Дисертації: "Local detection"

1

Marín, Tur Javier. "Pedestrian Detection based on Local Experts." Doctoral thesis, Universitat Autònoma de Barcelona, 2013. http://hdl.handle.net/10803/120187.

Повний текст джерела

Анотація:

Al llarg dels darrers anys, els sistemes de detecció humana basats en visió per computador han començat a exercir un paper clau en diverses aplicacions lligades a l’assisténcia a la conducció, la videovigilància, la robòtica i la domòtica. Detectar persones és, sens cap dubte, una de les tasques més difícils en el camp de la Visió per Computador. Aixó es deu principalment al grau de variabilitat en l’aparenc¸a humana associada a la roba, postura, forma i grandària. A més, altres factors com escenaris amb molts elements, oclusions parcials o condicions ambientals poden fer que la tasca de detecció sigui encara més difícil. Els mètodes més prometedors a l’estat de la q¨uestió es basen en models d’aprenentatge discriminatius que són entrenats amb exemples positius (vianants) i negatius (no vianants). El conjunt d’entrenament és un dels elements més rellevants a l’hora de construir un detector que faci front a la citada gran variabilitat. Per tal de crear el conjunt d’entrenament es requereix supervisió humana. L’inconvenient en aquest punt és el gran esforc¸ que suposa haver d’anotar, així com la tasca de cercar l’esmentada variabilitat. En aquesta tesi abordem dos problemes recurrents a l’estat de la q¨uestió. En la primera etapa, es pretén reduir l’esforc¸ d’anotar mitjanc¸ant l’ús de gràfics per computador. Més concretament, desenvolupemun escenari urbà permés endavant generar un conjunt d’entrenament. Tot seguit, entrenem un detector usant aquest conjunt, i finalment, avaluem si aquest detector pot ser aplicat amb èxit en un escenari real. En la segona etapa, ens centrem en millorar la robustesa dels nostres detectors en el cas en que els vianants es trobin parcialment ocluids. Més concretament, presentem un nou mètode de tractament d’oclusions que consisteix en millorar la detecció de sistemes holístics en cas de trobar un vianant parcialment ocluid. Per dur a terme aquesta millora, fem ús de classificadors (experts) locals a través d’un mètode anomenat random subspace method (RSM). Si el sistema holístic infereix que hi ha un vianant parcialment ocluid, aleshores s’aplica el RSM, el qual ha estat entrenat prèviament amb un conjunt que contenia vianants parcialment ocluids. L’últim objectiu d’aquesta tesi és proposar un detector de vianants fiable basat en un conjunt d’experts locals. Per aconseguir aquest objectiu, utilitzem el mètode anomenat random forest, a on els arbres es combinen per classificar i cada node és un expert local. En particular, cada expert local es centra en realitzar una classificació robusta de zones del cos. Cal remarcar, a més, que el nostre mètode presenta molta menys complexitat a nivell de disseny que altres mètodes de l’estat de la q¨uestió, alhora que ofereix una eficiència computacional raonable i una major precisió.
During the last decade vision-based human detection systems have started to play a key role in multiple applications linked to driver assistance, surveillance, robot sensing and home automation. Detecting humans is by far one of the most challenging tasks in Computer Vision. This is mainly due to the high degree of variability in the human appearance associated to the clothing, pose, shape and size. Besides, other factors such as cluttered scenarios, partial occlusions, or environmental conditions can make the detection task even harder. Most promising methods of the state-of-the-art rely on discriminative learning paradigms which are fed with positive and negative examples. The training data is one of the most relevant elements in order to build a robust detector as it has to cope the large variability of the target. In order to create this dataset human supervision is required. The drawback at this point is the arduous effort of annotating as well as looking for such claimed variability. In this PhD thesis we address two recurrent problems in the literature. In the first stage, we aim to reduce the consuming task of annotating, namely, by using computer graphics. More concretely, we develop a virtual urban scenario for later generating a pedestrian dataset. Then, we train a detector using this dataset, and finally we assess if this detector can be successfully applied in a real scenario. In the second stage, we focus on increasing the robustness of our pedestrian detectors under partial occlusions. In particular, we present a novel occlusion handling approach to increase the performance of block-based holistic methods under partial occlusions. For this purpose, we make use of local experts via a RandomSubspaceMethod (RSM) to handle these cases. If the method infers a possible partial occlusion, then the RSM, based on performance statistics obtained from partially occluded data, is applied. The last objective of this thesis is to propose a robust pedestrian detector based on an ensemble of local experts. To achieve this goal, we use the random forest paradigm, where the trees act as ensembles an their nodes are the local experts. In particular, each expert focus on performing a robust classification of a pedestrian body patch. This approach offers computational efficiency and far less design complexity when compared to other state-of-the-artmethods, while reaching better accuracy.

Стилі APA, Harvard, Vancouver, ISO та ін.

2

Ahlgren, Filip. "Local And Network Ransomware Detection Comparison." Thesis, Blekinge Tekniska Högskola, Institutionen för datavetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18291.

Повний текст джерела

Анотація:

Background. Ransomware is a malicious application encrypting important files on a victim's computer. The ransomware will ask the victim for a ransom to be paid through cryptocurrency. After the system is encrypted there is virtually no way to decrypt the files other than using the encryption key that is bought from the attacker. Objectives. In this practical experiment, we will examine how machine learning can be used to detect ransomware on a local and network level. The results will be compared to see which one has a better performance. Methods. Data is collected through malware and goodware databases and then analyzed in a virtual environment to extract system information and network logs. Different machine learning classifiers will be built from the extracted features in order to detect the ransomware. The classifiers will go through a performance evaluation and be compared with each other to find which one has the best performance. Results. According to the tests, local detection was both more accurate and stable than network detection. The local classifiers had an average accuracy of 96% while the best network classifier had an average accuracy of 89.6%. Conclusions. In this case the results show that local detection has better performance than network detection. However, this can be because the network features were not specific enough for a network classifier. The network performance could have been better if the ransomware samples consisted of fewer families so better features could have been selected.

Стилі APA, Harvard, Vancouver, ISO та ін.

3

Aytekin, Caglar. "Geo-spatial Object Detection Using Local Descriptors." Master's thesis, METU, 2011. http://etd.lib.metu.edu.tr/upload/12613488/index.pdf.

Повний текст джерела

Анотація:

There is an increasing trend towards object detection from aerial and satellite images. Most of the widely used object detection algorithms are based on local features. In such an approach, first, the local features are detected and described in an image, then a representation of the images are formed using these local features for supervised learning and these representations are used during classification . In this thesis, Harris and SIFT algorithms are used as local feature detector and SIFT approach is used as a local feature descriptor. Using these tools, Bag of Visual Words algorithm is examined in order to represent an image by the help of histograms of visual words. Finally, SVM classifier is trained by using positive and negative samples from a training set. In addition to the classical bag of visual words approach, two novel extensions are also proposed. As the first case, the visual words are weighted proportional to their importance of belonging to positive samples. The important features are basically the features occurring more in the object and less in the background. Secondly, a principal component analysis after forming the histograms is processed in order to remove the undesired redundancy and noise in the data, reduce the dimension of the data to yield better classifying performance. Based on the test results, it could be argued that the proposed approach is capable to detecting a number of geo-spatial objects, such as airplane or ships, for a reasonable performance.

Стилі APA, Harvard, Vancouver, ISO та ін.

4

Saigo, Hiroto. "Local alignment kernels for protein homology detection." 京都大学 (Kyoto University), 2006. http://hdl.handle.net/2433/135936.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

5

Beare, Richard. "Image segmentation based on local motion detection /." Title page, contents and abstract only, 1997. http://web4.library.adelaide.edu.au/theses/09PH/09phb3684.pdf.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

6

Donnelley, Martin, and martin donnelley@gmail com. "Computer Aided Long-Bone Segmentation and Fracture Detection." Flinders University. Engineering, 2008. http://catalogue.flinders.edu.au./local/adt/public/adt-SFU20080115.222927.

Повний текст джерела

Анотація:

Medical imaging has advanced at a tremendous rate since x-rays were discovered in 1895. Today, x-ray machines produce extremely high-quality images for radiologists to interpret. However, the methods of interpretation have only recently begun to be augmented by advances in computer technology. Computer aided diagnosis (CAD) systems that guide healthcare professionals to making the correct diagnosis are slowly becoming more prevalent throughout the medical field. Bone fractures are a relatively common occurrence. In most developed countries the number of fractures associated with age-related bone loss is increasing rapidly. Regardless of the treating physician's level of experience, accurate detection and evaluation of musculoskeletal trauma is often problematic. Each year, the presence of many fractures is missed during x-ray diagnosis. For a trauma patient, a mis-diagnosis can lead to ineffective patient management, increased dissatisfaction, and expensive litigation. As a result, detection of long-bone fractures is an important orthopaedic and radiologic problem, and it is proposed that a novel CAD system could help lower the miss rate. This thesis examines the development of such a system, for the detection of long-bone fractures. A number of image processing software algorithms useful for automating the fracture detection process have been created. The first algorithm is a non-linear scale-space smoothing technique that allows edge information to be extracted from the x-ray image. The degree of smoothing is controlled by the scale parameter, and allows the amount of image detail that should be retained to be adjusted for each stage of the analysis. The result is demonstrated to be superior to the Canny edge detection algorithm. The second utilises the edge information to determine a set of parameters that approximate the shaft of the long-bone. This is achieved using a modified Hough Transform, and specially designed peak and line endpoint detectors. The third stage uses the shaft approximation data to locate the bone centre-lines and then perform diaphysis segmentation to separate the diaphysis from the epiphyses. Two segmentation algorithms are presented and one is shown to not only produce better results, but also be suitable for application to all long-bone images. The final stage applies a gradient based fracture detection algorithm to the segmented regions. This algorithm utilises a tool called the gradient composite measure to identify abnormal regions, including fractures, within the image. These regions are then identified and highlighted if they are deemed to be part of a fracture. A database of fracture images from trauma patients was collected from the emergency department at the Flinders Medical Centre. From this complete set of images, a development set and test set were created. Experiments on the test set show that diaphysis segmentation and fracture detection are both performed with an accuracy of 83%. Therefore these tools can consistently identify the boundaries between the bone segments, and then accurately highlight midshaft long-bone fractures within the marked diaphysis. Two of the algorithms---the non-linear smoothing and Hough Transform---are relatively slow to compute. Methods of decreasing the diagnosis time were investigated, and a set of parallelised algorithms were designed. These algorithms significantly reduced the total calculation time, making use of the algorithm much more feasible. The thesis concludes with an outline of future research and proposed techniques that---along with the methods and results presented---will improve CAD systems for fracture detection, resulting in more accurate diagnosis of fractures, and a reduction of the fracture miss rate.

Стилі APA, Harvard, Vancouver, ISO та ін.

7

BERVANAKIS, GEORGE, and gberva@hotmail com. "DETECTION AND EXPRESSION OF BIOSYNTHETIC GENES IN ACTINOBACTERIA." Flinders University. School of Medicine, 2009. http://catalogue.flinders.edu.au./local/adt/public/adt-SFU20090531.033038.

Повний текст джерела

Анотація:

Most microbial organic molecules are secondary metabolites which consist of diverse chemical structures and a range of biological activities. Actinobacteria form a large group of Eubacteria that are prolific producers of these metabolites. The recurrence of pathogens resistant to antibiotics and a wider use of these metabolites apart from their use as anti-infectives, has been the impetus for pharmaceutical companies to search for compounds produced by rare and existing actinobacterial cultures. Accessing microbial biosynthetic pathway diversity has been possible through the use of sensitive and innovative molecular detection methodologies. The present study evaluated the use of molecular based screening as a rational approach to detect secondary metabolite biosynthetic genes (SMBG) in uncharacterised natural Actinobacterial populations. A polymerase chain reaction (PCR) approach was selected for ease of application and high sample processivity. Rational designed screening approaches using PCR in the discovery of SMBG, involved identifying common functions in secondary metabolite biosynthetic pathways, such as condensation reactions in polyketide synthesis, genes encoding these functions, and using conserved regions of these genes as templates for the design of primers to detect similar sequences in uncharacterised actinobacteria. Design of primers involved rigorous in silico analysis followed by experimentation and validation. PCR screening was applied to 22 uncharacterised environmental isolates, eight of these displayed the presence of the ketosynthase (KS) gene belonging to the type I polyketide synthases and eight contained the ketosynthase (KSÑ) gene belonging to the type II polyketide synthases, six of the isolates contained the presence of a presumptive dTDP-glucose synthase (strD) gene which is involved in the formation of deoxysugar components of aminoglycoside antibiotics and one isolate contained the presence of a presumptive isopenicillin N synthase (pcbC) gene involved in beta-lactam synthesis. Alignments of partially sequenced PCR products from isolates A1488 and A3023 obtained using type II PKS primers showed close similarities with KSÑ genes from antibiotic producing actinobacteria. Similarly, alignments of sequences from isolates A1113 and A0350 showed regions of similarities to KS genes from antibiotic producing actinobacteria. Fermentation techniques were used for inducing expression of secondary metabolites from the uncharacterised actinobacteria isolates. By using antimicrobial guided screening it was determined that most of the isolates possessed the capacity to produce antimicrobial metabolites. Dominant antagonistic activity was detected against Gram positive bacteria and to a minor extent against fungi. Optimal fermentation liquid media were identified for certain isolates for the production of antimicrobial metabolites. Two alternative fermentation methods; solid-state and liquid-oil fermentations were evaluated to improve secondary metabolite production in the uncharacterised isolates. Solid-substrate fermentation showed that it could induce a complex metabolite pattern by TLC analysis, however this pattern varied according to the substrate being used. Liquid media supplemented with refined oils, showed a positive response indicated by higher antibacterial activities detected. Evaluation of semi-purified organic extracts identified two isolates A1113 and A0350 producing similar antimicrobial metabolites as detected by HPLC/UV/MS, a literature database search of similar compounds containing the same molecular weight identified the compound as belonging to the actinomycin group of compounds. A complex metabolic pattern was identified for isolate A2381, database searching identified some of the compounds as having similar molecular weights to actinopyrones, trichostatins, antibiotics PI 220, WP 3688-5 and YL 01869P. Drug discovery screening can serve to benefit from PCR detection of biochemical genotypes in initial screens, providing a rapid approach in identifying secondary metabolite producing capabilities of microorganisms prior to the commencement of costly and time consuming fermentation studies. Additionally the identification of biochemical genotypes allows a directed approach in using fermentation media designed to induce biosynthetic pathways of specific classes of compounds.

Стилі APA, Harvard, Vancouver, ISO та ін.

8

Trauchessec, Vincent. "Local magnetic detection and stimulation of neuronal activity." Thesis, Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLS301/document.

Повний текст джерела

Анотація:

L’activité cérébrale se traduit par des courants ioniques circulant dans le réseau neuronal.La compréhension des mécanismes cérébraux implique de sonder ces courants, via des mesures électriques ou magnétiques, couvrant différentes échelles spatiales. A l’échelle cellulaire, les techniques d’électrophysiologie sont maitrisées depuis plusieurs décennies, mais il n’existe pas actuellement d’outils de mesure locale des champs magnétiques engendrés par les courants ioniques au sein du réseau neuronal. La magnéto-encéphalographie(MEG) utilise des SQUIDs(Superconducting QUantum Interference Devices)fonctionnant à très basse température, placés en surface du crâne, qui fournissent une cartographie des champs magnétiques mais dont la résolution spatiale est limitée du fait de la distance séparant les capteurs des cellules actives. Le travail présenté dans cette thèse propose de développer des capteurs magnétiques à la fois suffisamment sensibles pour être capable de détecter le champ magnétique extrêmement faible générés par les courants neuronaux (de l’ordre de 10⁻⁹ T), et dont la géométrie est adaptable aux dimensions des cellules, tout en fonctionnant à température ambiante. Ces capteurs,basés sur l’effet quantique de magnétorésistance géante (GMR, sont suffisamment miniaturisables pour être déposés à l’extrémité de sondes d’une finesse de l’ordre de 100 μm. L’utilisation de capteurs GMR pour la mesure de signaux biomagnétiques fut d’abord testée lors d’expériences in-vitro, réalisées sur le muscle soléaire de souris. Ce système biologique a été choisi pour sa simplicité,rendant la modélisation accessible, ainsi que pour sa robustesse, permettant d’avoir des résultats fiables et reproductibles. Le parfait accord entre les prédictions théoriques et les signaux magnétiques mesurés valide cette technologie. Enfin, des expériences in vivo dans le cortex visuel du chat ont permis de réaliser la toute première mesure de la signature magnétique de potentiels d’action générés par des neurones corticaux, ouvrant la voie à la magnétophysiologie
Information transmission in the brain occurs through ionic currents flowing inside the neuronal network. Understanding how the brain operates requires probing this electrical activity by measuring the associated electric or magnetic field. At the cellular scale, electrophysiology techniques are well mastered, but there is no tool to perform magnetophysiology. Mapping brain activity through the magnetic field generated by neuronal communication is done via magnetoencephalography (MEG). This technique is based on SQUIDs (Superconducting Quantum Interference Devices) that operate at liquid Helium temperature. This parameter implies to avoid any contact with living tissue and a shielding system that increases the distance between the neurons and the sensors, limiting spatial resolution. This thesis work aims at providing a new tool to performmagnetic recordings at the neuronal scale. The sensors developed during this thesis are based on the Giant Magneto-Resistance (GMR) effect. Operating at room temperature, they can be miniaturize and shaped according to the experiment, while exhibiting a sensitivity that allows to measure amplitude of 10⁻⁹ T. Before targeting neurons, the use of GMR-based sensors for magnetic recordings of biological activity has been validated through invitro experiments on the mouse soleus muscle. This biological system has been chosen because of its simple organization, allowing for a realistic modelling, and for its robustness, in order to get reliable and replicable results. The perfect agreement between the measurements and the theoretical predictions represents a consistent validation of the GMR technology for biological applications. Then a specially adapted needle-shaped probe carrying micron-sized GMR sensors has been developed for in-vivo experiment in cat visual cortex. The very first magnetic signature of action potentials inside the neuropil has been measured, paving the way towards magnetophysiology

Стилі APA, Harvard, Vancouver, ISO та ін.

9

Gill, Rupinder S. "Intrusion detection techniques in wireless local area networks." Thesis, Queensland University of Technology, 2009. https://eprints.qut.edu.au/29351/1/Rupinder_Gill_Thesis.pdf.

Повний текст джерела

Анотація:

This research investigates wireless intrusion detection techniques for detecting attacks on IEEE 802.11i Robust Secure Networks (RSNs). Despite using a variety of comprehensive preventative security measures, the RSNs remain vulnerable to a number of attacks. Failure of preventative measures to address all RSN vulnerabilities dictates the need for a comprehensive monitoring capability to detect all attacks on RSNs and also to proactively address potential security vulnerabilities by detecting security policy violations in the WLAN. This research proposes novel wireless intrusion detection techniques to address these monitoring requirements and also studies correlation of the generated alarms across wireless intrusion detection system (WIDS) sensors and the detection techniques themselves for greater reliability and robustness. The specific outcomes of this research are: A comprehensive review of the outstanding vulnerabilities and attacks in IEEE 802.11i RSNs. A comprehensive review of the wireless intrusion detection techniques currently available for detecting attacks on RSNs. Identification of the drawbacks and limitations of the currently available wireless intrusion detection techniques in detecting attacks on RSNs. Development of three novel wireless intrusion detection techniques for detecting RSN attacks and security policy violations in RSNs. Development of algorithms for each novel intrusion detection technique to correlate alarms across distributed sensors of a WIDS. Development of an algorithm for automatic attack scenario detection using cross detection technique correlation. Development of an algorithm to automatically assign priority to the detected attack scenario using cross detection technique correlation.

Стилі APA, Harvard, Vancouver, ISO та ін.

10

Gill, Rupinder S. "Intrusion detection techniques in wireless local area networks." Queensland University of Technology, 2009. http://eprints.qut.edu.au/29351/.

Повний текст джерела

Анотація:

This research investigates wireless intrusion detection techniques for detecting attacks on IEEE 802.11i Robust Secure Networks (RSNs). Despite using a variety of comprehensive preventative security measures, the RSNs remain vulnerable to a number of attacks. Failure of preventative measures to address all RSN vulnerabilities dictates the need for a comprehensive monitoring capability to detect all attacks on RSNs and also to proactively address potential security vulnerabilities by detecting security policy violations in the WLAN. This research proposes novel wireless intrusion detection techniques to address these monitoring requirements and also studies correlation of the generated alarms across wireless intrusion detection system (WIDS) sensors and the detection techniques themselves for greater reliability and robustness. The specific outcomes of this research are: A comprehensive review of the outstanding vulnerabilities and attacks in IEEE 802.11i RSNs. A comprehensive review of the wireless intrusion detection techniques currently available for detecting attacks on RSNs. Identification of the drawbacks and limitations of the currently available wireless intrusion detection techniques in detecting attacks on RSNs. Development of three novel wireless intrusion detection techniques for detecting RSN attacks and security policy violations in RSNs. Development of algorithms for each novel intrusion detection technique to correlate alarms across distributed sensors of a WIDS. Development of an algorithm for automatic attack scenario detection using cross detection technique correlation. Development of an algorithm to automatically assign priority to the detected attack scenario using cross detection technique correlation.

Стилі APA, Harvard, Vancouver, ISO та ін.

11

Rabbani, Seyedeh Parisa. "Effect of image variation on computer aided detection systems." Thesis, KTH, Skolan för teknik och hälsa (STH), 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-123546.

Повний текст джерела

Анотація:

Computer Aided Detection (CAD) systems are expecting to gain significant importance in terms of reducing the work load of radiologists and enabling the large screening programs. A large share of CAD systems are based on learning from examples, to enables the decision making between the images with or without disease. Images are simplified to numerical descriptors (features vectors) and the system is trained with these features. The common practical problem with CAD systems is training the system with a data from a specific source and testing it on a data from a different source; the variations between sources usually affect the CAD system function. The possible solutions for this problem are (1) normalizing images to make them look more equal, (2) choosing less variation sensitive features and (3) modifying the classifier so that it classifies the data from different sources more accurately. In this project the effect of image variations on the developed CAD system on chest radio graphs for Tuberculosis is studied at Diagnostic Image Analysis Group. Tuberculosis is one of the major healthcare problems in some parts of the world (1.3 million deaths in 2007) [1]. Although the system has a great performance on the train and test data from the same source, using different sub dataset for training and testing the system does not lead to the same result. To limit the effect of image variation of the CAD systems three different approaches are applied for normalizing the images: (1) Simple normalization, (2) local normalization and (3) multi band local normalization. All three approaches enhance the performance of the system in case of various sub datasets for training and testing purposes. According to the improvement achieved by applying normalization it is suggested as a solution for the stated problem above. Although the outcome of this study has satisfactory result, there is always room for further investigations and studies; in specific testing different approaches for finding less variation sensitive features and modifying the classification procedure to a more variation tolerant process.

Стилі APA, Harvard, Vancouver, ISO та ін.

12

Robbins, Benjamin John. "The detection of 2D image features using local energy." University of Western Australia. Dept. of Computer Science, 1996. http://theses.library.uwa.edu.au/adt-WU2003.0005.

Повний текст джерела

Анотація:

Accurate detection and localization of two dimensional (2D) image features (or 'key-points') is important for vision tasks such as structure from motion, stereo matching, and line labeling. 2D image features are ideal for these vision tasks because 2D image features are high in information and yet they occur sparsely in typical images. Several methods for the detection of 2D image features have already been developed. However, it is difficult to assess the performance of these methods because no one has produced an adequate definition of corners that encompasses all types of 2D luminance variations that make up 2D image features. The fact that there does not exist a consensus on the definition of 2D image features is not surprising given the confusion surrounding the definition of 1D image features. The general perception of 1D image features has been that they correspond to 'edges' in an image and so are points where the intensity gradient in some direction is a local maximum. The Sobel [68], Canny [7] and Marr-Hildreth [37] operators all use this model of 1D features, either implicitly or explicitly. However, other profiles in an image also make up valid 1D features, such as spike and roof profiles, as well as combinations of all these feature types. Spike and roof profiles can also be found by looking for points where the rate of change of the intensity gradient is locally maximal, as Canny did in defining a 'roof-detector' in much the same way he developed his 'edge-detector'. While this allows the detection of a wider variety of 1D features profiles, it comes no closer to the goal of unifying these different feature types to an encompassing definition of 1D features. The introduction of the local energy model of image features by Marrone and Owens [45] in 1987 provided a unified definition of 1D image features for the first time. They postulated that image features correspond to points in an image where there is maximal phase congruency in the frequency domain representation of the image. That is, image features correspond to points of maximal order in the phase domain of the image signal. These points of maximal phase congruency correspond to step-edge, roof, and ramp intensity profiles, and combinations thereof. They also correspond to the Mach bands perceived by humans in trapezoidal feature profiles. This thesis extends the notion of phase congruency to 2D image features. As 1D image features correspond to points of maximal 1D order in the phase domain of the image signal, this thesis contends that 2D image features correspond to maximal 2D order in this domain. These points of maximal 2D phase congruency include all the different types of 2D image features, including grey-level corners, line terminations, blobs, and a variety of junctions. Early attempts at 2D feature detection were simple 'corner detectors' based on a model of a grey-level corner in much the same way that early 1D feature detectors were based on a model of step-edges. Some recent attempts have included more complex models of 2D features, although this is basically a more complex a priori judgement of the types of luminance profiles that are to be labeled as 2D features. This thesis develops the 2D local energy feature detector based on a new, unified definition of 2D image features that marks points of locally maximum 2D order in the phase domain representation of the image as 2D image features. The performance of an implementation of 2D local energy is assessed, and compared to several existing methods of 2D feature detection. This thesis also shows that in contrast to most other methods of 2D feature detection, 2D local energy is an idempotent operator. The extension of phase congruency to 2D image features also unifies the detection of image features. 1D and 2D image features correspond to 1D and 2D order in the phase domain respresentation of the image respectively. This definition imposes a hierarchy of image features, with 2D image features being a subset of 1D image features. This ordering of image features has been implied ever since 1D features were used as candidate points for 2D feature detection by Kitchen [28] and others. Local energy enables the extraction of both 1D and 2D image features in a consistent manner; 2D image features are extracted from the 1D image features using the same operations that are used to extract 1D image features from the input image. The consistent approach to the detection of image features presented in this thesis allows the hierarchy of primitive image features to be naturally extended to higher order image features. These higher order image features can then also be extracted from higher order image data using the same hierarchical approach. This thesis shows how local energy can be naturally extended to the detection of 1D (surface) and higher order image features in 3D data sets. Results are presented for the detection of 1D image features in 3D confocal microscope images, showing superior performance to the 3D extension of the Sobel operator [74].

Стилі APA, Harvard, Vancouver, ISO та ін.

13

Mora, Maria Alejandra Mol André. "Detection of longitudinal tooth fractures using Local Computed Tomography." Chapel Hill, N.C. : University of North Carolina at Chapel Hill, 2006. http://dc.lib.unc.edu/u?/etd,536.

Повний текст джерела

Анотація:

Thesis (M.S.)--University of North Carolina at Chapel Hill, 2006.
Title from electronic title page (viewed Oct. 10, 2007). "... in partial fulfillment of the requirements for the degree of Master of Science in the Department of Diagnostic Sciences and General Dentistry, School of Dentistry." Discipline: Diagnostic Sciences and General Dentistry; Department/School: Dentistry.

Стилі APA, Harvard, Vancouver, ISO та ін.

14

Shakeel, Asif. "Enhanced squeezing in homodyne detection via local-oscillator optimization." Thesis, Massachusetts Institute of Technology, 1995. http://hdl.handle.net/1721.1/37025.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

15

Zhang, Ziming. "Efficient object detection via structured learning and local classifiers." Thesis, Oxford Brookes University, 2013. https://radar.brookes.ac.uk/radar/items/420cfbee-bf00-4d53-be8b-04f83389994f/1.

Повний текст джерела

Анотація:

Object detection has made great strides recently. However, it is still facing two big challenges: detection accuracy and computational efficiency. In this thesis, we present an automatic efficient object detection frarnework to detect object instances ·in images using bounding boxes, which can be trained and tested easily on current personal computers. Our framework is a sliding-window based approach, and consists of two major components: (1) efficient object proposal generation, predicting possible object bounding boxes, and (2) efficient object proposal verification, classifying each bounding box in a multiclass manner. For object proposal generation, we formulate this problem as a structured learning problem and investigate structural support vector machines (SSVMs) with our proposed scale/aspect-ratio quantization scheme and ranking constraints. A general ranking-order decomposition algorithm is developed for solving the formulation efficiently, and applied to generate proposals using a two-stage cascade. Using image gradients as features, our object proposal generation method achieves state-of-the-art results in terms Df object recall at a low cost in computation. For object proposal verification, we propose two locally linear and one locally nonlinear classifiers to approximate the nonlinear decision boundaries in the feature space efficiently. Inspired by the kernel trick, these classifiers map the original features into another feature space explicitly where linear classifiers are employed for classification, and thus have linear computational complexity in both training and testing, similar to that of linear classifiers. Therefore, in general, our classifiers can achieve comparable accuracy to kernel based classifiers at the cost of lower computational time. To demonstrate its efficiency and generality, our framework is applied to four different object detection tasks: VOC detection challenges, traffic sign detection, pedestrian detection, and face detection. In each task, it can perform reasonably well with acceptable detection accuracy and good computational efficiency. For instance, on VOC datasets with 20 object classes, our method achieved about 0.1 mean average precision (AP) within 2 hours of training and 0.05 second of testing a 500 x 300 pixel image using a mixture of MATLAB and C++ code on a current personal computer.

Стилі APA, Harvard, Vancouver, ISO та ін.

16

Andersson, Martina. "Local, intestinal biomarkers for early detection of colorectal cancer." Thesis, Uppsala universitet, Institutionen för farmaci, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-445701.

Повний текст джерела

Анотація:

Colorectal cancer (CRC) is one of the deadliest cancers in the world. The early stage of the disease is usually asymptomatic and therefore screening methods for colorectal cancer need to improve. There is a need for early detection of CRC as treatment is less effective in the advanced stage of the disease. The current standard screening methods are endoscopy and fecal immunochemical blood tests. Endoscopy is a commonly used method to diagnose the patient, but it is costly, time consuming, and rather unpopular for the patients. An alternative could be to develop targeted molecular imaging probes that specifically deliver agents for example magnetic resonance imaging to colon adenomas and adenocarcinomas. This alternative would be non-invasive and able to detect the disease before morphological changes become evident. Biomarkers are used as an objective indicator of an altered biological process. Here, a literature study was conducted to identify protein biomarkers that are overexpressed in early stages of CRC. This study has focused on biomarkers that could be used to target imaging agents to cancerous lesions. Thus, the biomarkers need to be membrane-bound and expressed on the luminal side of the gastrointestinal tract. This will help future research to develop orally administered targeted imaging probes. Furthermore, a smaller literature search was conducted to identify cell and mouse models representing early stages of CRC. This was done to facilitate translational research going from in vitro to in vivo. Ideally the same protein is available in cell lines, mouse models and humans to enable translational research. This work has resulted in the selection of 7 different proteins that are upregulated during early stages of CRC. These proteins are potentially apically located and therefore possible targets for monoclonal antibodies. These findings might lead to a novel way for preventive patient screening and hopefully reduce the mortality for colorectal cancer.

Стилі APA, Harvard, Vancouver, ISO та ін.

17

Belmonte, Romain. "Facial landmark detection with local and global motion modeling." Thesis, Lille 1, 2019. http://www.theses.fr/2019LIL1I066/document.

Повний текст джерела

Анотація:

La détection des points caractéristiques du visage est une tâche essentielle pour un grand nombre d’applications telles que l’analyse faciale (p. ex., identification, expression, reconstruction 3D), l’interaction homme-machine ou encore le multimédia (p. ex., recherche, indexation). Bien que de nombreuses approches aient été proposées, les performances en conditions non contrôlées ne sont toujours pas satisfaisantes. Les variations susceptibles d’impacter l’apparence du visage (p. ex., pose, expression, éclairage, occultation, flou cinétique) en font un problème encore difficile à résoudre. Dans cette thèse, une contribution est faite à la fois sur l’analyse des performances des approches actuelles mais aussi sur la modélisation de l’information temporelle pour la détection des points caractéristiques du visage basée sur la vidéo. Une étude expérimentale est réalisée à l’aide d’un jeu de données vidéo permettant d’évaluer l’impact des variations de pose et d’expression sur la détection des points caractéristiques. Cette évaluation permet notamment de mettre en évidence les poses et expressions posant le plus de difficultés. Elle permet également d’illustrer l’importance d’une modélisation temporelle capable de tenir compte efficacement de la nature dynamique du visage. L’accent est ensuite mis sur l’amélioration de la modélisation temporelle afin de considérer le mouvement local en plus du mouvement global. Plusieurs architectures sont conçues en s’appuyant sur les deux principaux modèles de la littérature : les réseaux de régression de coordonnées et les réseaux de régression de cartes de chaleur. Les expérimentations sur deux ensembles de données confirment que la modélisation du mouvement local améliore les résultats (p. ex. avec les expressions). Ces expérimentations sont étendues par une étude portant sur la complémentarité entre l’information spatiale et temporelle ainsi que le mouvement local et global dans le but d’améliorer la conception des architectures proposées. En exploitant davantage ces complémentarités, de meilleures performances, compétitives avec l’état de l’art, sont obtenues, et ce, malgré la simplicité des modèles proposés
Facial landmark detection is an essential task for a large number of applications such as facial analysis (e.g., identification, expression, 3D reconstruction), human-computer interaction or even multimedia (e.g., content indexing and retrieval). Although many approaches have been proposed, performance under uncontrolled conditions is still not satisfactory. The variations that may impact facial appearance (e.g., pose, expression, illumination, occlusion, motion blur) make it a difficult problem to solve. In this thesis, a contribution to both the analysis of the performance of current approaches and the modeling of temporal information for video-based facial landmark detection is made. An experimental study is conducted using a video dataset to measure the impact of pose and expression variations on landmark detection. This evaluation highlights the most difficult poses and expressions to handle. It also illustrates the importance of a suitable temporal modeling to benefit from the dynamic nature of the face. A focus is then placed on improving temporal modeling to ensure consideration of local motion in addition to global motion. Several architectures are designed based on the two main models from the literature: coordinate regression networks and heatmap regression networks. Experiments on two datasets confirm that local motion modeling improves results (e.g. in the presence of expressions). These experiments are extended with a study on the complementarity between spatial and temporal information as well as local and global motion to improve the design of the proposed architectures. By leveraging these complementarities more effectively, competitive performance with current state-of-the-art approaches is achieved, despite the simplicity of the proposed models

Стилі APA, Harvard, Vancouver, ISO та ін.

18

Ma, Fei, and feim@csem flinders edu au. "Registration of mass-like objects in sequential mammograms using graph matching." Flinders University. School of Computer Science, Engineering & Mathematics, 2008. http://catalogue.flinders.edu.au./local/adt/public/adt-SFU20090323.155040.

Повний текст джерела

Анотація:

Sequential mammograms contain important information, such as changes of the breast or developments of the masses, for diagnosis of disease. Comparison of sequential mammograms plays an important part for radiologists in identifying malignant masses. However, currently computer-aided detection (CAD) programs can not use such information eciently. The diculties lie in the registration of sequential mammograms. Most of current methods register sequential mammograms based on control points and image transformations. For these methods to work, extraction and correspondence of the control points is essential. This thesis presents a new approach in registering mammograms. The proposed method registers mammograms by associating mass-like objects in sequential mammograms directly. The mass-like objects appear in the images of normal breasts as well as images of breast with cancer. When the mass-like objects in sequential mammograms are accurately associated, measurements of changes in mass-like objects over time become possible. This is an important way to distinguish mass-like objects associated with cancer from cysts or other benign objects. The proposed method is based on graph matching. It uses the internal structure of the breast represented by the spatial relation between the mass-like objects to establish a correspondence between the sequential mammograms. In this method, the mammogram is firstly segmented into separate components using an adaptive pyramid (AP) segmentation algorithm. A series of filters, based on the features of components, is then applied to the components to remove the undesired ones. The remaining components, the mass-like objects, are represented by a complete graph. The spatial relations between the remaining mass-like objects are expressed by fuzzy spatial relation representation and are associated to the edges of the graph as weights. Association of the mass-like objects of two sequential mammograms is realized by finding a common subgraph of the corresponding two graphs using the backtrack algorithm. The segmentation methods developed in the course of this work were tested on a separate problem in computer-aided detection of breast cancer, namely the automatic extraction of the pectoral muscle. The graph matching method was tested independently of the segmentation method on artificially distorted mammograms and the full process, including the segmentation and the graph matching, was evaluated on 95 temporal mammogram pairs. The present implementation indicates only a small improvement in cancer detection rates but also presents opportunities for a substantial development of the basic method in the future.

Стилі APA, Harvard, Vancouver, ISO та ін.

19

Ngonmang, Kaledje Christel Blaise. "Detection and dynamic of local communities in large social networks." Thesis, Paris 13, 2014. http://www.theses.fr/2014PA132057/document.

Повний текст джерела

Анотація:

Les réseaux sont présents dans plusieurs contextes et applications : biologie, transports, réseaux sociaux en ligne, etc. De nombreuses applications récentes traitent d'immenses volumes de données personnelles. Les liens entre les personnes dans ces données peuvent traduire des liens d'amitiés, des échanges de messages, ou des intérêts communs. Les entités impliquées dans les réseaux, et spécialement les personnes, ont tendance à former des communautés. Dans ce contexte, une communauté peut être définie comme un ensemble d'entités qui interagissent beaucoup plus entre elles qu'avec le reste du réseau. La détection de communautés dans les grands réseaux a largement été étudiée pendant ces dernières années, suite aux travaux précurseurs de Newman qui a introduit le critère de modularité. Toutefois, la majorité des algorithmes de détection de communautés supposent que le réseau est complètement connu et qu'il n'évolue pas avec le temps. Dans cette thèse, nous commençons par proposer de nouvelles méthodes pour la détection de communautés locales (en considérant uniquement le voisinage d'un nœud donné et sans accéder à la totalité du réseau). Nos algorithmes sont plus efficaces que ceux de l'état de l'art. Nous montrons ensuite comment utiliser les communautés détectées pour améliorer la prévision de comportements utilisateurs. Dans un deuxième temps, nous proposons des approches pour prévoir l'évolution des communautés détectées. Ces méthodes sont basées sur des techniques d'apprentissage automatique. Enfin, nous proposons un framework général pour stocker et analyser les réseaux distribués dans un environnement "Big Data" . Les méthodes proposées sont validées en utilisant (entre autre) des données réelles issues d'un partenaire industriel fournissant un des réseaux en ligne les plus utilisés en France (40 millions d'utilisateurs)
Complex networks arises in many contexts and applications : biology, transports, online social networks (ONS). Many recent applications deal with large amount of personal data. The links between peoples may reflect freindship, messaging, or some common interests. Entities in complex network, and espacially persons, tend to form communities. Here, a community can be defined as a set of entities interacting more between each other than with the rest of the network. The topic of community detection in large networks as been extensively studied during the last decades, following the seminal work by newman, who popularized the modularity criteria. However, most community detection algorithms assume that the network is entirely known and that is does not evolve with time. This is usually not true in real world applications. In this thesis, we start by proposing novel methods for local community identification (considering only the vicinity of a given node, without accessing the whole graph). Our algorithms experimentally outperform the state-of-art methods. We show how to use the local communities to enhance the prediction of a user's behaviour. Secondly, we propose some approaches to predict the evolution of the detected communities based on machine learning methods. Finally we propose a framework for storing and processing distributed social networks in a Big Data environment. The proposed methods are validated using (among others) real world data, provided by a industrial partner operating a major social network platform in France (40 millions of users)

Стилі APA, Harvard, Vancouver, ISO та ін.

20

Lee, Boon Chuan. "Local interaction simulation approach for damage detection with Lamb waves." Thesis, University of Sheffield, 2005. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.425488.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

21

Wenngren, Wilhelm Sven Ingemar. "Local pulse wave velocity detection over an arterial segment using photoplethysmography." University of British Columbia, 2017. http://hdl.handle.net/2429/63867.

Повний текст джерела

Анотація:

The goal of this thesis is to determine the validity of using photoplethysmography (the detection of changes of blood volume using light) to measure pulse wave velocity as part of a continuous and non-disruptive blood pressure monitor. There has been a limited advancement over the years in technologies to monitor personal blood pressure, which have rendered at-home monitoring still relatively intrusive. The main method for at-home blood pressure monitoring is the use of an inflating cuff that obstructs the artery to detect pressure. This system suffers from inherit drawbacks, such as limitations on recording accuracy if insufficient time has passed between samples and the restrictive nature of the cuff which can induce pain on a user. An alternative device that can monitor continuously would thus benefit people who are sensitive or need 24-hour monitoring. Ideally this would be a system that can be worn without discomfort and does not interfere with the user in any way. The ideal device would also allow continuous blood pressure monitoring throughout the cardiac cycle, independent of the level of physical activity of the user. Furthermore, this type of device would allow athletes to measure blood pressure during activity. To this end, a model is developed to describe blood pressure by measuring the arterial diameter on the radial artery and the pulse wave velocity (PWV) through it. Research suggests that these two metrics, along with the elasticity of an artery, can be used as a means to measure blood pressure non-invasively. This thesis focuses on the measurement of pulse wave velocity. The system design, including the hardware, is covered. The analysis techniques used to obtain raw signals, as well as the methods used to determine the PWV, will be discussed. The measurement location is described in detail. The results are shown to be comparable to values found in literature. However, due to lack of comparable measurement techniques, no direct comparisons between methods could be performed.
Applied Science, Faculty of
Engineering, School of (Okanagan)
Graduate

Стилі APA, Harvard, Vancouver, ISO та ін.

22

Yu, Meng. "Facial feature detection and tracking with a 3D constrained local model." Thesis, University of St Andrews, 2010. http://hdl.handle.net/10023/2124.

Повний текст джерела

Анотація:

This thesis establishes a framework for facial feature detection and human face movement tracking. Statistical models of shape and appearance are built to represent the human face structure and interpret target images of human faces. The approach is a patch-based method derived from an earlier proposed method, the constrained local model (CLM) [1] algorithm. In order to increase the ability to track face movements with large head rotations, a 3D shape model is used in the system. And multiple texture models from different viewpoints are used to model the appearance. During fitting or tracking, the current estimate of pose (shape coordinates) is used to select the appropriate texture model. The algorithm uses the shape model and a texture model to generate a set of region template detectors. A search is then performed in the global pose / shape space using these detectors. Different optimisation frameworks are used in the implementation. The training images are created by rendering expressive 3D face models with different scales, rotations, expressions, brightness, etc. Experimental results are demonstrated by fitting the model to image sequences with large head rotations to evaluate the performance of the algorithm. To evaluate the stability and selection of factors of the algorithm, more experiments are carried out. The results show that the proposed 3D constrained local model algorithm improves the performance of the original CLM algorithm for videos with large out-of-plane head rotations.

Стилі APA, Harvard, Vancouver, ISO та ін.

23

Caruso, Laure. "Giant magnetoresistance based sensors for local magnetic detection of neuronal currents." Thesis, Paris 6, 2015. http://www.theses.fr/2015PA066272/document.

Повний текст джерела

Анотація:

L'étude de l'activité cérébrale nécessite des enregistrements simultanés à différentes échelles spatiales, d'une cellule unique aux aires corticales du cerveau. Ces mesures fournissent un aperçu sur la relation entre les structures, les fonctions et la dynamique des circuits neuronaux. Les techniques d'électrophysiologie apportent des informations cruciales sur l'activité électrique dans les neurones. Sonder localement la signature magnétique de cette activité donne des informations directes sur les courants neuronaux et la nature vectorielle d'une mesure magnétique renseigne sur la directionnalité du flux ionique neuronal sans le perturber. Le champ magnétique induit par les courants neuronaux est accessible par la magnetoencéphalographie (MEG), qui fournit la cartographie des champs neuromagnétiques à la surface du cerveau à l'aide des Superconducting Quantum Interference Devices (SQUIDs). Cependant, les mesures locales de courants neuronaux à l'échelle cellulaire nécessite des dispositifs miniaturisés et très sensibles. L'objectif de ce travail de thèse est de développer un nouvel outil pour la neurophysiologie, l'équivalent magnétique d'électrodes, nommé "magnetrodes", capable de détecter les courants neuronaux locaux par la détection magnétique. Les progrès récents de l'électronique de spin ont permis de donner naissance aux capteurs à magnétorésistance géante (GMR), qui offrent la possibilité d'être miniaturisé et suffisamment sensibles pour détecter des champs magnétiques très faibles, comme ceux émis par les neurones à l'échelle locale (de l'ordre du picotesla au nanotesla). Deux types de capteurs GMRs ont été développés au cours de ce travail, des sondes planes dédiées aux enregistrements en surface des tissues (tranche d'hippocampe, muscle ou cortex), les autres sont des sondes pointus, conçus pour pénétrer facilement les tissus et enregistrer localement les champs neuromagnétiques. Trois expériences ont été réalisées dont deux in vitro et une in vivo. Le premier potentiel d'action magnétique a été détecté in vitro à l'aide de sondes GMRs planes, résultant des courants axiaux dans un muscle de la souris. Le deuxième modèle analysé in vitro est la tranche d'hippocampe de cerveau de souris où les deux types de sondes ont été testés, montrant certains résultats préliminaires. Enfin, nous avons effectué les premiers enregistrements magnétiques in vivo sur le cortex visuel du chat, affichant des réponses corticales induites de l'ordre de 10-20 nTpp. Ces résultats ouvrent la voie à magnetophysiologie locale qui est une nouvelle approche d'exploration et d'interfaçage cerveau
Understanding brain activity requires simultaneous recordings across spatial scales, from single-cell to brain-wide network. Measurements provide insights about the relationship between structures, functions and dynamics in neuronal circuits and assemblies. Electrophysiological techniques carry crucial information about the electrical activity within neurons. Locally probing the magnetic signature of this activity gives direct information about neuronal currents and the vectorial nature of magnetic measurements provides the directionality of neuronal ionic flux without disturbing it. Noticeably, the magnetic signature induced by the neuronal currents is accessible through Magneto EncephaloGraphy (MEG), which provides neuromagnetic field mapping outside the head using Superconducting QUantum Interference Devices (SQUIDs). However, local measurements of neuronal currents at cellular scale requires small and very sensitive devices. The purpose of the present thesis work is to develop a novel tool for neurophysiology, the magnetic equivalent of electrodes, named “magnetrodes”, are able to detect the local neuronal currents through magnetic detection. Recent advances in spin electronics have given rise to Giant MagnetoResistance (GMR) based sensors, which offer the possibility to be miniaturized and sensitive enough to detect very weak magnetic fields like those emitted by neurons at local scale (in the picotesla to nanotesla range). Two kinds of GMR based sensors have been developed throughout this work, one of these are planar probes dedicated to surface measurements (hippocampus slice, muscle or cortex), the other kind are sharp probes, designed in a needle-shape to easily penetrate the tissues and locally record the neuromagnetic fields. Three experiments have been performed, either in vitro and in vivo. In the first experiment, an Action Potential has been detected magnetically in vitro by means of planar GMR sensors, resulting from axial currents within a mouse muscle. The second in vitro experiment analyzed the hippocampal mouse brain slices, where both planar and sharp probes were tested giving some preliminary results. Lastly we performed the first magnetic recordings in vivo on cat's cerebral cortex, displaying stimulus-induced cortical responses of 10-20 nT pp . These results pave the way for local magnetophysiology, a novel approach of brain exploration and interfacing

Стилі APA, Harvard, Vancouver, ISO та ін.

24

Le, Viet Phuong. "Logo detection, recognition and spotting in context by matching local visual features." Thesis, La Rochelle, 2015. http://www.theses.fr/2015LAROS029/document.

Повний текст джерела

Анотація:

Cette thèse présente un framework pour le logo spotting appliqué à repérer les logos à partir de l’image des documents en se concentrant sur la catégorisation de documents et les problèmes de récupération de documents. Nous présentons également trois méthodes de matching par point clé : le point clé simple avec le plus proche voisin, le matching par règle des deux voisins les plus proches et le matching par deux descripteurs locaux à différents étapes de matching. Les deux derniers procédés sont des améliorations de la première méthode. En outre, utiliser la méthode de classification basée sur la densité pour regrouper les correspondances dans le framework proposé peut aider non seulement à segmenter la région candidate du logo mais également à rejeter les correspondances incorrectes comme des valeurs aberrantes. En outre, afin de maximiser la performance et de localiser les logos, un algorithme à deux étages a été proposé pour la vérification géométrique basée sur l’homographie avec RANSAC. Comme les approches fondées sur le point clé supposent des approches coûteuses, nous avons également investi dans l’optimisation de notre framework. Les problèmes de séparation de texte/graphique sont étudiés. Nous proposons une méthode de segmentation de texte et non-texte dans les images de documents basée sur un ensemble de fonctionnalités puissantes de composants connectés. Nous avons appliqué les techniques de réduction de dimensionnalité pour réduire le vecteur de descripteurs locaux de grande dimension et rapprocher les algorithmes de recherche du voisin le plus proche pour optimiser le framework. En outre, nous avons également mené des expériences pour un système de récupération de documents sur les documents texte et non-texte segmentés et l'algorithme ANN. Les résultats montrent que le temps de calcul du système diminue brusquement de 56% tandis que la précision diminue légèrement de près de 2,5%. Dans l'ensemble, nous avons proposé une approche efficace et efficiente pour résoudre le problème de spotting des logos dans les images de documents. Nous avons conçu notre approche pour être flexible pour des futures améliorations. Nous croyons que notre travail peut être considéré comme une étape sur la voie pour résoudre le problème de l’analyse complète et la compréhension des images de documents
This thesis presents a logo spotting framework applied to spotting logo images on document images and focused on document categorization and document retrieval problems. We also present three key-point matching methods: simple key-point matching with nearest neighbor, matching by 2-nearest neighbor matching rule method and matching by two local descriptors at different matching stages. The last two matching methods are improvements of the first method. In addition, using a density-based clustering method to group the matches in our proposed spotting framework can help not only segment the candidate logo region but also reject the incorrect matches as outliers. Moreover, to maximize the performance and to locate logos, an algorithm with two stages is proposed for geometric verification based on homography with RANSAC. Since key-point-based approaches assume costly approaches, we have also invested to optimize our proposed framework. The problems of text/graphics separation are studied. We propose a method for segmenting text and non-text in document images based on a set of powerful connected component features. We applied dimensionality reduction techniques to reduce the high dimensional vector of local descriptors and approximate nearest neighbor search algorithms to optimize our proposed framework. In addition, we have also conducted experiments for a document retrieval system on the text and non-text segmented documents and ANN algorithm. The results show that the computation time of the system decreases sharply by 56% while its accuracy decreases slightly by nearly 2.5%. Overall, we have proposed an effective and efficient approach for solving the problem of logo spotting in document images. We have designed our approach to be flexible for future improvements by us and by other researchers. We believe that our work could be considered as a step in the direction of solving the problem of complete analysis and understanding of document images

Стилі APA, Harvard, Vancouver, ISO та ін.

25

Okuyama, Satoshi. "Application of SAR interferometry to detection of local deformations in Izu-Oshima." 京都大学 (Kyoto University), 2006. http://hdl.handle.net/2433/144190.

Повний текст джерела

Анотація:

Kyoto University (京都大学)
0048
新制・課程博士
博士(理学)
甲第12107号
理博第3001号
新制||理||1447(附属図書館)
23943
UT51-2006-J102
京都大学大学院理学研究科地球惑星科学専攻
(主査)教授竹本修三, 助教授福田洋一, 教授橋本学
学位規則第4条第1項該当

Стилі APA, Harvard, Vancouver, ISO та ін.

26

Madrigali, Andrea. "Analysis of Local Search Methods for 3D Data." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2016.

Знайти повний текст джерела

Анотація:

In questa tesi sono stati analizzati alcuni metodi di ricerca per dati 3D. Viene illustrata una panoramica generale sul campo della Computer Vision, sullo stato dell’arte dei sensori per l’acquisizione e su alcuni dei formati utilizzati per la descrizione di dati 3D. In seguito è stato fatto un approfondimento sulla 3D Object Recognition dove, oltre ad essere descritto l’intero processo di matching tra Local Features, è stata fatta una focalizzazione sulla fase di detection dei punti salienti. In particolare è stato analizzato un Learned Keypoint detector, basato su tecniche di apprendimento di machine learning. Quest ultimo viene illustrato con l’implementazione di due algoritmi di ricerca di vicini: uno esauriente (K-d tree) e uno approssimato (Radial Search). Sono state riportate infine alcune valutazioni sperimentali in termini di efficienza e velocità del detector implementato con diversi metodi di ricerca, mostrando l’effettivo miglioramento di performance senza una considerabile perdita di accuratezza con la ricerca approssimata.

Стилі APA, Harvard, Vancouver, ISO та ін.

27

Zheng, Lining. "Distributed Local Outlier Factor with Locality-Sensitive Hashing." Thesis, Université d'Ottawa / University of Ottawa, 2019. http://hdl.handle.net/10393/39817.

Повний текст джерела

Анотація:

Outlier detection remains a heated area due to its essential role in a wide range of applications, including intrusion detection, fraud detection in finance, medical diagnosis, etc. Local Outlier Factor (LOF) has been one of the most influential outlier detection techniques over the past decades. LOF has distinctive advantages on skewed datasets with regions of various densities. However, the traditional centralized LOF faces new challenges in the era of big data and no longer satisfies the rigid time constraints required by many modern applications, due to its expensive computation overhead. A few researchers have explored the distributed solution of LOF, but existant methods are limited by their grid-based data partitioning strategy, which falls short when applied to high-dimensional data. In this thesis, we study efficient distributed solutions for LOF. A baseline MapReduce solution for LOF implemented with Apache Spark, named MR-LOF, is introduced. We demonstrate its disadvantages in communication cost and execution time through complexity analysis and experimental evaluation. Then an approximate LOF method is proposed, which relies on locality-sensitive hashing (LSH) for partitioning data and enables fully distributed local computation. We name it MR-LOF-LSH. To further improve the approximate LOF, we introduce a process called cross-partition updating. With cross-partition updating, the actual global k-nearest neighbors (k-NN) of the outlier candidates are found, and the related information of the neighbors is used to update the outlier scores of the candidates. The experimental results show that MR-LOF achieves a speedup of up to 29 times over the centralized LOF. MR-LOF-LSH further reduces the execution time by a factor of up to 9.9 compared to MR-LOF. The results also highlight that MR-LOF-LSH scales well as the cluster size increases. Moreover, with a sufficient candidate size, MR-LOF-LSH is able to detect in most scenarios over 90% of the top outliers with the highest LOF scores computed by the centralized LOF algorithm.

Стилі APA, Harvard, Vancouver, ISO та ін.

28

Senthil, Rathna. "IDLE: A Novel Approach to Improving Overlapping Community Detection in Complex Networks." Thesis, Virginia Tech, 2016. http://hdl.handle.net/10919/65160.

Повний текст джерела

Анотація:

Complex systems in areas such as biology, physics, social science, and technology are extensively modeled as networks due to the rich set of tools available for their study and analysis. In such networks, groups of nodes that correspond to functional units or those that share some common attributes result in densely connected structures called communities. Community formation is an inherent process, and it is not easy to detect these structures because of the complex ways in which components of these systems interact. Detecting communities in complex networks is important because it helps us to understand their internal dynamics better, thereby leading to significant insights into the underlying systems. Overlapping communities are formed when nodes in the network simultaneously belong to more than one community, and it has been shown that most real networks naturally contain such an overlapping community structure. In this thesis, I introduce a new approach to overlapping community detection called IDLE that incorporates ideas from another interesting problem: the identification of influential spreaders. Influential spreaders are nodes that play an important role in the propagation of information or diseases in networks. Research suggests that the main core identified by k-core decomposition techniques are the most influential spreaders. In my approach, I use these k-cores as candidate seeds for local community detection. Following a well-defined seed selection process, IDLE builds and prunes their corresponding local communities. It then augments the resulting local communities and puts them together to obtain the global overlapping community structure of the network. My approach improves on the current local community detection techniques, because they use either random nodes or maximal k-cliques as seeds, and they do not focus explicitly on detecting overlapping nodes in the network. Hence their results can be significantly improved in building ground-truth overlapping communities. The results of my experiments on real and synthetic networks indicate that IDLE results in enhanced overlapping community detection and thereby a better identification of overlapping nodes that could be important or influential components in the underlying system.
Master of Science

Стилі APA, Harvard, Vancouver, ISO та ін.

29

Wang, Benjamin. "Lip Detection and Adaptive Tracking." DigitalCommons@CalPoly, 2017. https://digitalcommons.calpoly.edu/theses/1695.

Повний текст джерела

Анотація:

Performance of automatic speech recognition (ASR) systems utilizing only acoustic information degrades significantly in noisy environments such as a car cabins. Incorporating audio and visual information together can improve performance in these situations. This work proposes a lip detection and tracking algorithm to serve as a visual front end to an audio-visual automatic speech recognition (AVASR) system. Several color spaces are examined that are effective for segmenting lips from skin pixels. These color components and several features are used to characterize lips and to train cascaded lip detectors. Pre- and post-processing techniques are employed to maximize detector accuracy. The trained lip detector is incorporated into an adaptive mean-shift tracking algorithm for tracking lips in a car cabin environment. The resulting detector achieves 96.8% accuracy, and the tracker is shown to recover and adapt in scenarios where mean-shift alone fails.

Стилі APA, Harvard, Vancouver, ISO та ін.

30

Ali, Imtiaz. "Object Detection in Dynamic Background." Thesis, Lyon 2, 2012. http://www.theses.fr/2012LYO20008/document.

Повний текст джерела

Анотація:

La détection et la reconnaissance d’objets dans des vidéos numériques est l’un des principaux challenges dans de nombreuses applications de vidéo surveillance. Dans le cadre de cette thèse, nous nous sommes attaqué au problème difficile de la segmentation d’objets dans des vidéos dont le fond est en mouvement permanent. Il s’agit de situations qui se produisent par exemple lorsque l’on filme des cours d’eau, ou le ciel,ou encore une scène contenant de la fumée, de la pluie, etc. Il s’agit d’un sujet assez peu étudié dans la littérature car très souvent les scènes traitées sont plutôt statiques et seules quelques parties bougent, telles que les feuillages par exemple, ou les seuls mouvements sont des changements de luminosité. La principale difficulté dans le cadre des scènes dont le fond est en mouvement est de différencier le mouvement de l’objet du mouvement du fond qui peuvent parfois être très similaires. En effet, par exemple, un objet dans une rivière peut se déplacer à la même allure que l’eau. Les algorithmes de la littérature extrayant des champs de déplacement échouent alors et ceux basés sur des modélisations de fond génèrent de très nombreuses erreurs. C’est donc dans ce cadre compliqué que nous avons tenté d’apporter des solutions.La segmentation d’objets pouvant se baser sur différents critères : couleur, texture,forme, mouvement, nous avons proposé différentes méthodes prenant en compte un ou plusieurs de ces critères.Dans un premier temps, nous avons travaillé dans un contexte bien précis qui était celui de la détection des bois morts dans des rivières. Ce problème nous a été apporté par des géographes avec qui nous avons collaboré dans le cadre du projet DADEC (Détection Automatique de Débris pour l’Aide à l’Etude des Crues). Dans ce cadre, nous avons proposé deux méthodes l’une dite " naïve " basée sur la couleur des objets à détecter et sur leur mouvement et l’autre, basée sur une approche probabiliste mettant en oeuvre une modélisation de la couleur de l’objet et également basée sur leur déplacement. Nous avons proposé une méthode pour le comptage des bois morts en utilisant les résultats des segmentations.Dans un deuxième temps, supposant la connaissance a priori du mouvement des objets,dans un contexte quelconque, nous avons proposé un modèle de mouvement de l’objet et avons montré que la prise en compte de cet a priori de mouvement permettait d’améliorer nettement les résultats des segmentations obtenus par les principaux algorithmes de modélisation de fond que l’on trouve dans la littérature.Enfin, dans un troisième temps, en s’inspirant de méthodes utilisées pour caractériser des textures 2D, nous avons proposé un modèle de fond basé sur une approche fréquentielle.Plus précisément, le modèle prend en compte non seulement le voisinage spatial d’un pixel mais également le voisinage temporel de ce dernier. Nous avons appliqué la transformée de Fourier locale au voisinage spatiotemporel d’un pixel pour construire un modèle de fond.Nous avons appliqué nos méthodes sur plusieurs vidéos, notamment les vidéos du projet DADEC, les vidéos de la base DynTex, des vidéos synthétiques et des vidéos que nous avons faites
Moving object detection is one of the main challenges in many video monitoring applications.In this thesis, we address the difficult problem that consists in object segmentation when background moves permanently. Such situations occur when the background contains water flow, smoke or flames, snowfall, rainfall etc. Object detection in moving background was not studied much in the literature so far. Video backgrounds studied in the literature are often composed of static scenes or only contain a small portion of moving regions (for example, fluttering leaves or brightness changes). The main difficulty when we study such situations is to differentiate the objects movements and the background movements that may be almost similar. For example, an object in river moves at the same speed as water. Therefore, motion-based techniques of the literature, relying on displacements vectors in the scene, may fail to discriminate objects from the background, thus generating a lot of false detections. In this complex context, we propose some solutions for object detection.Object segmentation can be based on different criteria including color, texture, shape and motion. We propose various methods taking into account one or more of these criteria.We first work on the specific context of wood detection in rivers. It is a part of DADEC project (Détection Automatique de Débris pour l’Aide à l’Etude des Crues) in collaboration with geographers. We propose two approaches for wood detection: a naïve method and the probabilistic image model. The naïve approach is based on binary decisions based on object color and motion, whereas the probabilistic image model uses wood intensity distribution with pixel motion. Such detection methods are used fortracking and counting pieces of wood in rivers.Secondly, we consider a context in which we suppose a priori knowledge about objectmotion is available. Hence, we propose to model and incorporate this knowledge into the detection process. We show that combining this prior motion knowledge with classical background model improves object detection rate.Finally, drawing our inspiration from methods used for 2D texture representation, we propose to model moving backgrounds using a frequency-based approach. More precisely, the model takes into account the spatial neighborhoods of pixels but also their temporal neighborhoods. We apply local Fourier transform on the obtained regions in order to extract spatiotemporal color patterns.We apply our methods on multiple videos, including river videos under DADEC project, image sequences from the DynTex video database, several synthetic videos andsome of our own made videos. We compare our object detection results with the existing methods for real and synthetic videos quantitatively as well as qualitatively

Стилі APA, Harvard, Vancouver, ISO та ін.

31

Gundogdu, Erhan. "Feature Detection And Matching Towards Augmented Reality Applications On Mobile Devices." Master's thesis, METU, 2012. http://etd.lib.metu.edu.tr/upload/12614618/index.pdf.

Повний текст джерела

Анотація:

Local feature detection and its applications in different problems are quite popular in vision research. In order to analyze a scene, its invariant features, which are distinguishable in many views of this scene, are used in pose estimation, object detection and augmented reality. However, required performance metrics might change according to the application type
in general, the main metrics are accepted as accuracy and computational complexity. The contributions in this thesis provide improving these metrics and can be divided into three parts, as local feature detection, local feature description and description matching in different views of the same scene. In this thesis an efficient feature detection algorithm with sufficient repeatability performance is proposed. This detection method is convenient for real-time applications. For local description, a novel local binary pattern outperforming state-of-the-art binary pattern is proposed. As a final task, a fuzzy decision tree method is presented for approximate nearest neighbor search. In all parts of the system, computational efficiency is considered and the algorithms are designed according to limited processing time. Finally, an overall system capable of matching different views of the same scene has been proposed and executed in a mobile platform. The results are quite promising such that the presented system can be used in real-time applications, such as augmented reality, object retrieval, object tracking and pose estimation.

Стилі APA, Harvard, Vancouver, ISO та ін.

32

Asbach, Mark [Verfasser]. "Modeling for part-based visual object detection based on local features / Mark Asbach." Aachen : Hochschulbibliothek der Rheinisch-Westfälischen Technischen Hochschule Aachen, 2012. http://d-nb.info/1021938211/34.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

33

Hajdarevic, Kemal. "Early detection of network problems using existing network indicators : local agent based approach." Thesis, Leeds Beckett University, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.446160.

Повний текст джерела

Анотація:

Everyday business operation depends on reliable computer and network infrastructure. There are different threats that can cause serious problems to the operation of system resources, such as intrusion, denial of service attacks and performance loss situations. Every day the media reveal incidents that cause major losses of money and reputation in organizations and companies affected by these events. Detecting problems such as performance loss and attacks in their early development stages would save money for the owners of systems. If early stages of unwanted events can be identified in time, it should be possible to proactively (before they are affected) protect managed systems against incidents and failures. To be able to detect and stop attacks or performance loss, accurate mechanisms are needed to perform these actions in time and the approach described in this thesis takes timing into consideration as one of the most important elements in problem resolution. Another important element for proactive problem resolution is data, which have to be easily accessible and available so that the time spent in collection and processing is less than the time needed for the problem to escalate. In this thesis a set of data which can be found in management information base (MIB) is used for problem resolution. The MIB data set contains relevant data which can be used for resolution of different problems. Local agents can be used to speed up the process of detection and proactive prevention of problematic situations since all tasks are performed locally. This thesis presents different experimental scenarios from already seen incidents such as attacks and performance loss situations. It also proposes a system for proactive problem resolution by using already available hardware components, thus avoiding the need to invest in the additional hardware required by many other proposed solutions. Additional hardware usually adds complexity to an already complex infrastructure, and this can be avoided by using the approach described in this thesis.

Стилі APA, Harvard, Vancouver, ISO та ін.

34

Mikolajczyk, Krystian. "Detection of local features invariant to affine transformations : application to matching and recognition." Grenoble INPG, 2002. http://www.theses.fr/2002INPG0053.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

35

Johansson, Stefan. "Earthquake Analysis Using a Migration Based Detection Algorithm Applied to Local Earthquake Data." Thesis, Uppsala universitet, Geofysik, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-325373.

Повний текст джерела

Анотація:

In this study earthquake data is analyzed using a newly developed Migration Based Detection (MBD) algorithm (Wagner et al. 2017). A software environment suitable for manual analysis of large quantities of earthquakes (events) detected by the MBD algorithm is set up, and the MBD algorithm is applied to 13 days of seismic data from a network of 26 seismic stations in the geologically complex Hengill-area in southwest Iceland. A total of 859 event detections are produced and manually inspected. Out of these, 483 are considered true and/or uncertain, making the assessed number of false detections about 44%. A subset of 53 well defined true events are selected for event relocation using manual picking of first arrival P-waves. The relocation resulted in a mean difference of roughly 0.6 km for each coordinate in the horizontal plane and about 1.4 km in depth. Results of the study provide reference data that may aid further development of the MBD algorithm, as well as provide some insight into the performance of the MBD algorithm. The software environment tailored for analyzing events detected by the MBD algorithm may be used as a foundation for continued analysis of detected events.
I denna studie analyserades jordskalvsdata med hjälp av en nyligen utvecklad 'migration based detection'-algoritm (Wagner et al. 2017). En mjukvarumiljö skräddarsydd för manuell analys av stora kvantiteter av jordskalv detekterade av MBD-algoritmen iordningställdes, varpå MBD-algoritmen sedan applicerades på 13 dagar av seismisk data från ett nätverk av 26 seismiska stationer i det geologiskt sett komplexa Hengill-området i sydvästra Island. Totalt detekterades 859 jordskalv som genomgick manuell analys. Av dessa klassificerades 483 stycken som bekräftade eller troliga jordskalv, vilket resulterar i en uppskattad felmarginal om ca. 44 %. En delmängd om 53 väldefinierade jordskalv valdes ut för noggrannare analys av ursprungsplats och tidpunkt genom manuell plockning av P-fasankomst. Omlokaliseringen resulterade i en genomsnittlig differens om ca. 0.6 km i vardera koordinat i horisontalplanet och ca. 1.4 km i höjdled. Resultat från projektet kan användas som referensdata vid vidareutveckling av MBD-algoritmen samt ger viss insyn i prestandan hos MBD-algoritmen. Den iordningställda datormiljön kan användas som bas för vidare analys av jordskalv detekterade av MBD-algoritmen.

Стилі APA, Harvard, Vancouver, ISO та ін.

36

Tran, Antoine. "Object representation in local feature spaces : application to real-time tracking and detection." Thesis, Université Paris-Saclay (ComUE), 2017. http://www.theses.fr/2017SACLY010/document.

Повний текст джерела

Анотація:

La représentation visuelle est un problème fondamental en vision par ordinateur. Le but est de réduire l'information au strict nécessaire pour une tâche désirée. Plusieurs types de représentation existent, comme les caractéristiques de couleur (histogrammes, attributs de couleurs...), de forme (dérivées, points d'intérêt...) ou d'autres, comme les bancs de filtres.Les caractéristiques bas-niveau (locales) sont rapides à calculer. Elles ont un pouvoir de représentation limité, mais leur généricité présente un intérêt pour des systèmes autonomes et multi-tâches, puisque les caractéristiques haut-niveau découlent d'elles.Le but de cette thèse est de construire puis d'étudier l'impact de représentations fondées seulement sur des caractéristiques locales de bas-niveau (couleurs, dérivées spatiales) pour deux tâches : la poursuite d'objets génériques, nécessitant des caractéristiques robustes aux variations d'aspect de l'objet et du contexte au cours du temps; la détection d'objets, où la représentation doit décrire une classe d'objets en tenant compte des variations intra-classe. Plutôt que de construire des descripteurs d'objets globaux dédiés, nous nous appuyons entièrement sur les caractéristiques locales et sur des mécanismes statistiques flexibles visant à estimer leur distribution (histogrammes) et leurs co-occurrences (Transformée de Hough Généralisée). La Transformée de Hough Généralisée (THG), créée pour la détection de formes quelconques, consiste à créer une structure de données représentant un objet, une classe... Cette structure, d'abord indexée par l'orientation du gradient, a été étendue à d'autres caractéristiques. Travaillant sur des caractéristiques locales, nous voulons rester proche de la THG originale.En poursuite d'objets, après avoir présenté nos premiers travaux, combinant la THG avec un filtre particulaire (utilisant un histogramme de couleurs), nous présentons un algorithme plus léger et rapide (100fps), plus précis et robuste. Nous présentons une évaluation qualitative et étudierons l'impact des caractéristiques utilisées (espace de couleur, formulation des dérivées partielles...). En détection, nous avons utilisé l'algorithme de Gall appelé forêts de Hough. Notre but est de réduire l'espace de caractéristiques utilisé par Gall, en supprimant celles de type HOG, pour ne garder que les dérivées partielles et les caractéristiques de couleur. Pour compenser cette réduction, nous avons amélioré deux étapes de l'entraînement : le support des descripteurs locaux (patchs) est partiellement produit selon une mesure géométrique, et l'entraînement des nœuds se fait en générant une carte de probabilité spécifique prenant en compte les patchs utilisés pour cette étape. Avec l'espace de caractéristiques réduit, le détecteur n'est pas plus précis. Avec les mêmes caractéristiques que Gall, sur une même durée d'entraînement, nos travaux ont permis d'avoir des résultats identiques, mais avec une variance plus faible et donc une meilleure répétabilité
Visual representation is a fundamental problem in computer vision. The aim is to reduce the information to the strict necessary for a query task. Many types of representation exist, like color features (histograms, color attributes...), shape ones (derivatives, keypoints...) or filterbanks.Low-level (and local) features are fast to compute. Their power of representation are limited, but their genericity have an interest for autonomous or multi-task systems, as higher level ones derivate from them. We aim to build, then study impact of low-level and local feature spaces (color and derivatives only) for two tasks: generic object tracking, requiring features robust to object and environment's aspect changes over the time; object detection, for which the representation should describe object class and cope with intra-class variations.Then, rather than using global object descriptors, we use entirely local features and statisticals mecanisms to estimate their distribution (histograms) and their co-occurrences (Generalized Hough Transform).The Generalized Hough Transform (GHT), created for detection of any shape, consists in building a codebook, originally indexed by gradient orientation, then to diverse features, modeling an object, a class. As we work on local features, we aim to remain close to the original GHT.In tracking, after presenting preliminary works combining the GHT with a particle filter (using color histograms), we present a lighter and fast (100 fps) tracker, more accurate and robust.We present a qualitative evaluation and study the impact of used features (color space, spatial derivative formulation).In detection, we used Gall's Hough Forest. We aim to reduce Gall's feature space and discard HOG features, to keep only derivatives and color ones.To compensate the reduction, we enhanced two steps: the support of local descriptors (patches) are partially chosen using a geometrical measure, and node training is done by using a specific probability map based on patches used at this step.With reduced feature space, the detector is less accurate than with Gall's feature space, but for the same training time, our works lead to identical results, but with higher stability and then better repeatability

Стилі APA, Harvard, Vancouver, ISO та ін.

37

Perret, Matias Nicholas. "Local optical phase detection probes with an application to a high speed boundary layer." Diss., University of Iowa, 2016. https://ir.uiowa.edu/etd/2129.

Повний текст джерела

Анотація:

This thesis presents the continued development of micro optical phase detection instrumentation capable of measuring void fraction, interfacial area density, interfacial velocity and bubble sizes and their application to measurements in a high speed boundary layer. The instrumentation consists of micro sized sapphire tipped probes tailored to measure in the two-phase flow of air bubbles in water. Probe tips with geometries intended to maximize field life while minimizing intrusiveness were designed, fabricated and characterized. The characterization revealed that the active region of a probe tip can go beyond the highly sensitive 45 degree tip. Controlling the active length of the tips can be achieved through a combination of taper angles and 45 degree tip size, with larger tips having shorter active lengths. The full scale bubbly flow measurements were performed on a 6 m flat bottom survey boat. The aforementioned quantities were measured on bubbles naturally entrained at the bow of the boat. Probes were positioned at the bow of the boat, near the entrainment region and at the stern where the bubbles exit after having interacted with the high shear turbulent boundary layer. Experiments were conducted in fresh water, at the Coralville Lake, IA, and salt water, at the St. Andrews Bay and Gulf Coast near Panama City, FL. The results indicate that the bubbles interact significantly with the boundary layer. At low speeds, in fresh water, bubble accumulation and coalescence is evident by the presence of large bubbles at the stern. At high speeds, in both fresh and salt water, bubble breakup dominates and very small bubbles are produced near the hull of the boat. It was observed that salt water inhibits coalescence, even at low boat speeds. Void fraction was seen to increase with boat speeds above 10 knots and peaks near the wall. Bubble velocities show slip with the wall at all speeds and exhibit large RMS fluctuations, increasing near the wall.

Стилі APA, Harvard, Vancouver, ISO та ін.

38

Wu, Yubao. "Efficient and Effective Local Algorithms for Analyzing Massive Graphs." Case Western Reserve University School of Graduate Studies / OhioLINK, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=case1454451336.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

39

Alamgir, Nyma. "Computer vision based smoke and fire detection for outdoor environments." Thesis, Queensland University of Technology, 2020. https://eprints.qut.edu.au/201654/1/Nyma_Alamgir_Thesis.pdf.

Повний текст джерела

Анотація:

Surveillance Video-based detection of outdoor smoke and fire has been a challenging task due to the chaotic variations of shapes, movement, colour, texture, and density. This thesis contributes to the advancement of the contemporary efforts of smoke and fire detection by proposing novel technical methods and their possible integration into a complete fire safety model. The novel contributions of this thesis include an efficient feature calculation method combining local and global texture properties, the development of deep learning-based models and a conceptual framework to incorporate weather information in the fire safety model for improved accuracy in fire prediction and detection.

Стилі APA, Harvard, Vancouver, ISO та ін.

40

Abt, Tin Lian. "Detection of a Local Mass Anomaly in the Shallow Subsurface by Applying a Matched Filter." The Ohio State University, 2011. http://rave.ohiolink.edu/etdc/view?acc_num=osu1313154731.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

41

White, Shane Paul White. "Study of Heavy Metal/Ferromagnetic Films Using Electrical Detection and Local Ferromagnetic Resonance Force Microscopy." The Ohio State University, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=osu1524172007784423.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

42

Chen, Chuxing. "Local atmospheric electricity and its possible application in high-energy cosmic ray air shower detection." Diss., The University of Arizona, 1989. http://hdl.handle.net/10150/184799.

Повний текст джерела

Анотація:

We have conducted an extensive experimental study on the subject of near ground atmospheric electricity. The main objective was to gain more understanding of this particular aspect of atmospheric phenomena, while testing the possible application to cosmic ray research. The results in atmospheric electricity show that there are certain patterns in ion grouping such as the size and lifetime. The average lifetime of ion group is 0.7 seconds and the average size is about 10 meters at our experimental site. Ultrahigh energy cosmic ray air showers should create sizable slow atmospheric electric pulses according to our theoretical calculations. Preliminary studies on air showers with total particle number N equal or greater than 10⁵ (10¹⁵ eV) have yielded strong evidence that slow atmospheric current pulses are associated with air showers. The theory and the experiment agree with each other fairly well when we average over large numbers of events. With our current experimental arrangement, when the air shower exceeds a certain size, the system response saturates. Therefore it is extremely desirable in future research that the counter array be designed for a much higher threshold level, since this prototype experiment indicates that interesting data would be obtained. Another reason for further experimental research being directed toward ultrahigh energy, e.g., N ≥ 10⁷ (10¹⁷ eV) and higher, is to establish a calibration of the slow atmospheric electric signals generated by cosmic rays as a function of primary cosmic ray energy and core location. This type of slow atmospheric electric signal, if fully understood and calibrated, offers a new and potentially less expensive technique to observe ultrahigh energy cosmic ray events, which hold some fundamental keys to the knowledge of the universe on a large scale.

Стилі APA, Harvard, Vancouver, ISO та ін.

43

Chen, Shin-an, and 陳信安. "Local Sensor Fault Detection." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/51467149371373062679.

Повний текст джерела

Анотація:

碩士
元智大學
電機工程研究所
89
This thesis investigates the problem of local sensor fault detection. The conventional approach is to filter out the low frequency normal signal with high pass filter before detection. We point out that detecting the sensor fault after high-pass filtering is problematic. For example, the energy of the fault signal “change of bias” is concentrate in low frequencies. After high-pass filtering, most of the energy disappears and the detection fails. We propose to use the unfiltered sensor output signal directly to detect sensor fault. Events like Bias-change, Noise-increase or Jump occurs can be detected by observing the sample mean、sample variance and normalized sample. Four types of sensor faults: Bias、Drift、Erratic and Spike can be detected based on the observations. In the simulations, we use both synthetic signals generated from a mathematical model and earthquake real-measured data to detect sensor faults. We also propose to use soft decisions that correspond to fault degrees between 0 and 1, which provide more information compare to the “0” or “1” hard decision.

Стилі APA, Harvard, Vancouver, ISO та ін.

44

張芝榮. "Relative Centrality and Local Community Detection." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/47791975490821202491.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

45

Wu, Chan-Wei, and 吳展維. "Channel-Aware Distributed Binary Detection with Unknown Local Sensor Detection Probability." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/89795682750674031944.

Повний текст джерела

Анотація:

碩士
國立交通大學
電信工程系所
97
In the field of wireless sensor networks, existing works of channel-aware fusion rule design assume that the fusion center (FC) knows the local sensor detection probabilities. However, this paradigm ignores the possibility of unknown sensor alarm responses to the event occurrences. This work focuses on the case where the local detection probability is unknown and assumes sensors transmit their one-bit reports through binary symmetric channels to FC. Traditionally, Generalized Likelihood Ratio Test (GLRT) can tackle this scenario, but it does not guarantee optimal performance and is too complicated to analyze. To solve these problems, a simpler fusion rule is proposed based on the simplified ML estimate, and its performance is analyzed. By investigating the channel effects, a power allocation scheme is then proposed to further improve the performance. Being far less complicated than GLRT, the proposed fusion rule with power allocation outperforms GLRT significantly and can even achieve the performance of LRT, which is the optimal rule for any possible detectors.

Стилі APA, Harvard, Vancouver, ISO та ін.

46

Peng, Shen-Chieh, and 彭聖傑. "Smoke Detection Using Global and Local Features." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/35942372244330965413.

Повний текст джерела

Анотація:

碩士
國立交通大學
生醫工程研究所
99
This study presents a novel smoke detection approach using local feature analysis and global feature verification. Studies have investigated visual-based smoke detection techniques in surveillance systems for years. However, given an image in open or large spaces with typical smoke and disturbances of commonly moving objects such as pedestrians or vehicles, detecting smoke without false alarm is still a challenging problem. It is important to find features to distinguish smoke from various environments. This study analyzes characteristics of candidate blocks in video sequences to exploit local features: edge blurring, gradual energy change and gradual color configuration change. Each local feature is strong enough to detect smoke with few false alarms. Moreover, proposed features are complementary to each other. Hence, local features are combined to lower the false alarm rates by boosting cascade architecture. To further overcome some false situation, global feature verification is proposed to gather statistics of information on contour and in the whole area of each candidate region. Experimental results show that the proposed system can well detect smoke with low false alarm rate within a short reaction time in various environments. The whole system can run in real time and has been implemented on embedded system.

Стилі APA, Harvard, Vancouver, ISO та ін.

47

Chen, Jung-Bow, and 陳中寶. "Face detection based on local color texture." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/09578835892851533958.

Повний текст джерела

Анотація:

碩士
玄奘大學
資訊科學學系碩士班
95
In biometrics authentication, face recognition is usually used as the core technology, and face detection is one of the most important work in face recognition. The main propose in face detection is to use the image to find if a subimage is the human’s face or not and to draw the existence area, so that it is easier to do further recognition works. In the literature, there have many methods to execute the task of the face detection. For example, they are Template matching, Neural network approach, Color-based approach, etc, but only a few of them use the feature of the color texture in face detection. They proposed Color Wavelet Covariance (CWC) and Wavelet Transform (WT) technologies and bringing out the suitable method for face detection. A method which can use the specific color texture feature on the face, is proposed in this paper. Using statistic measures to find out the color texture vector, the support vector machine (SVM) classifier is used to discriminate faces and non-faces. The support vector machine can be used to complete a complicated static image, and to provide a effective face detection.

Стилі APA, Harvard, Vancouver, ISO та ін.

48

Zhi-JiaJian and 簡志佳. "CLOSE: Local Community Detection by LOcal Structure Expansion in a Complex Network." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/8vf89j.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

49

Huang, Ssu-Neng, and 黃偲能. "Region Duplication Detection Based on Image Invariant Feature and Local Outlier Detection." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/mb82u9.

Повний текст джерела

Анотація:

碩士
國立臺北科技大學
電機工程系研究所
99
Nowadays image editing software is so sophisticated that one can easily tamper digital images without leaving any obvious traces. To develop an automatic tampering detection algorithm becomes an important issue. Region duplication is a common and simple way of digital image tampering. Recent methods based on sparse feature descriptor matching can detect the region duplication with lower geometrical and illumination distortion, where past methods could fail, but they are still imperfect for the detection of duplicated regions imposed with stronger distortion of affine transform and rotation. Furthermore, all the existing methods will mistakenly classify the intrinsic repeated elements as duplication tamping. Our method stems from sparse feature descriptor matching approach. We propose a new matching method for higher distortion and a local outlier detection method to analyze the distribution of image invariant feature on image space for intrinsic repeated elements. We evaluate our proposed approach on a set of automatically synthesized forgery images with duplicated, distorted regions and intrinsic repeated elements. The experimental results show that our proposed method is robust and effective in region duplication detection.

Стилі APA, Harvard, Vancouver, ISO та ін.

50

Tao, Chun-Hao, and 陶君浩. "Compare the Detection Result by Using Different Local Item Dependent Detection Methods." Thesis, 2012. http://ndltd.ncl.edu.tw/handle/81568550699907328582.

Повний текст джерела

Анотація:

碩士
國立臺灣師範大學
教育心理與輔導學系
101
The purpose of this research is to compare the detection result by using testlet effect estimates of the Rasch testlet model, testlet-residual based principal component analysis and the Q3 statistics. The research is composed of two sub-researches. Study 1 is a simulation study. In study 1, first, testlet effects (high/ low), sample sizes (500/1500) and the item numbers within testlet (2/4/6/8) were manipulated. Testlet effect estimates of the Rasch testlet model, testlet-residual based principal component analysis and the Q3 statistics were used to detected local item dependent for each testlet. The parameters recovery of testlet effect, the detection result of testlet-residual based principal component analysis and the Q3 statistics, and the Spearman's ρ coefficient of local item dependent detection result with the true value of testlet effect were used to compare the detection result of different local item dependent detection methods. Study 2 is an empirical study. These three local item dependent detection methods were compared and applied to the data from the English subject of Basic Competence Test for Junior High School Students(2004～2009). The main results are the following： 1.As sample sizes and the item numbers in each testlet were increased, the parameters recovery of testlet effect decreased to an acceptable level. It means the testlet effect estimates of the Rasch testlet model will be more and more accurate when the sample sizes or item numbers increases. However, in the condition of high testlet effect, the estimated accuracy of testlet effect were decreased instead. 2.No matter in what situations, the detection result of the Q3 statistics was better than the other two detection methods. 3.The detection results have varied between these three local item dependent detection methods on the english subject of Basic Competence Test for Junior High School Students(2004～2009), testlet effect estimates of the Rasch testlet model especially. 4.According to the detection result of the Q3 statistics, there were no local item dependent for each testlet on the english subject of Basic Competence Test for Junior High School Students(2004～2009), except for 93-2-3, 93-2-5, 93-2-6, 94-1-8, and 97-2-3 .

Стилі APA, Harvard, Vancouver, ISO та ін.

Дисертації з теми "Local detection"

Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями