To see the other types of publications on this topic, follow the link: RECOGNITION APPLICATIONS.
Dissertations / Theses on the topic 'RECOGNITION APPLICATIONS'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'RECOGNITION APPLICATIONS.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Olausson, Erik. "Face Recognition for Mobile Phone Applications." Thesis, Linköping University, Department of Science and Technology, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-11850.
Full textAbstract:
Att applicera ansiktsigenkänning direkt på en mobiltelefon är en utmanande uppgift, inte minst med tanke på den begränsade minnes- och processorkapaciteten samt den stora variationen med avseende på ansiktsuttryck, hållning och ljusförhållande i inmatade bilder.
Det är fortfarande långt kvar till ett färdigutvecklat, robust och helautomatiskt ansiktsigenkänningssystem för den här miljön. Men resultaten i det här arbetet visar att genom att plocka ut feature-värden från lokala regioner samt applicera en välgjord warpstrategi för att minska problemen med variationer i position och rotation av huvudet, är det möjligt att uppnå rimliga och användbara igenkänningsnivåer. Speciellt för ett halvautomatiskt system där användaren har sista ordet om vem personen på bilden faktiskt är.
Med ett galleri bestående av 85 personer och endast en referensbild per person nådde systemet en igenkänningsgrad på 60% på en svårklassificerad serie testbilder. Totalt 73% av gångerna var den rätta individen inom de fyra främsta gissningarna.
Att lägga till extra referensbilder till galleriet höjer igenkänningsgraden rejält, till nästan 75% för helt korrekta gissningar och till 83,5% för topp fyra. Detta visar att en strategi där inmatade bilder läggs till som referensbilder i galleriet efterhand som de identifieras skulle löna sig ordentligt och göra systemet bättre efter hand likt en inlärningsprocess.
Detta exjobb belönades med pris för "Bästa industrirelevanta bidrag" vid Svenska sällskapet för automatiserad bildanalys årliga konferens i Lund, 13-14 mars 2008.
Applying face recognition directly on a mobile phone is a challenging proposal due to the unrestrained nature of input images and limitations in memory and processor capabilities.
A robust, fully automatic recognition system for this environment is still a far way off. However, results show that using local feature extraction and a warping scheme to reduce pose variation problems, it is possible to capitalize on high error tolerance and reach reasonable recognition rates, especially for a semi-automatic classification system where the user has the final say.
With a gallery of 85 individuals and only one gallery image per individual available the system is able to recognize close to 60 % of the faces in a very challenging test set, while the correct individual is in the top four guesses 73% of the time.
Adding extra reference images boosts performance to nearly 75% correct recognition and 83.5% in the top four guesses. This suggests a strategy where extra reference images are added one by one after correct classification, mimicking an online learning strategy.
2
Thompson, J. R. "Applications of pattern recognition in medicine." Thesis, Open University, 1985. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.377939.
Full text
3
Al-Rajab, Moaath. "Hand gesture recognition for multimedia applications." Thesis, University of Leeds, 2008. http://etheses.whiterose.ac.uk/607/.
Full textAbstract:
Hand gesture is potentially a very natural and useful modality for human-machine interaction. It is considered to be one of the most complicated and interesting challenges in computer vision due to its articulated structure and environmental variations. Solving such challenges requires robust hand detection, feature description, and viewpoint invariant classification. This thesis introduces several steps to tackle these challenges and applies them in a hand-gesture-based application (a game) to demonstrate the proposed approach. Techniques on new feature description, hand gesture detection and viewpoint invariant methods are explored and evaluated. A normal webcam is used in the research as input device. Hands are segmented using pre-trained skin colour models and tracked using the CAMShift tracker. Moment invariants are used as a shape descriptor. A new approach utilising the Zernike Velocity Moments (ZVMs, first introduced by Shutler and Nixon [1,2]), is examined on hand gestures. Results obtained using the ZVMs as spatial-temporal descriptor are compared to an HMM with Zemike moments (ZMs). Manually isolated hand gestures are used as input to the ZVM descriptor which generates vectors of features that are classified using a regression classifier. The performance of ZVM is evaluated using isolated, user-independent and user-dependent data. Isolating (segmenting) the gesture manually from a video stream for gesture recognition is a research proposition only and real life scenarios require an automatic hand gesture detection mechanism. Two methods for detecting gestures are examined. Firstly, hand gesture detection is performed using a sliding window which segments sequences of frames and then evaluates them against pre-trained HMMs. Secondly, the set of class-specific HMMs is combined into a single HMM and the Viterbi algorithm is then used to find the optimal sequence of gestures. Finally, the thesis proposes a flexible application that provides the user with options to perform the gesture from different viewpoints. A usable hand gesture recognition system should be able to cope with such viewpoint variations. To solve this problem, a new approach is introduced which makes use of 3D models of hand gestures (not postures) for generating projections. A virtual arm with 3D models of real hands is created. After that, virtual movements of the hand are simulated using animation software and projected from different viewpoints. Using a multi-Gaussian HMM, the system is trained on the projected sequences. Each set of hand gesture projections is marked with its specific class and used to train the single multi-class HMNI with gestures across different viewpoints.
4
Muller, Neil Leonard. "Image recognition using the Eigenpicture Technique (with specific applications in face recognition and optical character recognition)." Master's thesis, University of Cape Town, 1998. http://hdl.handle.net/11427/14381.
Full textAbstract:
Includes bibliographical references.In the first part of this dissertation, we present a detailed description of the eigenface technique first proposed by Sirovich and Kirby and subsequently developed by several groups, most notably the Media Lab at MIT. Other significant contributions have been made by Rockefeller University, whose ideas have culminated in a commercial system known as Faceit. For a different techniques (i.e. not eigenfaces) and a detailed comparison of some other techniques, the reader is referred to [5]. Although we followed ideas in the open literature (we believe there that there is a large body of advanced proprietary knowledge, which remains inaccessible), the implementation is our own. In addition, we believe that the method for updating the eigenfaces to deal with badly represented images presented in section 2. 7 is our own. The next stage in this section would be to develop an experimental system that can be extensively tested. At this point however, another, nonscientific difficulty arises, that of developing an adequately large data base. The basic problem is that one needs a training set representative of all faces to be encountered in future. Note that this does not mean that one can only deal with faces in the database, the whole idea is to be able to work with any facial image. However, a data base is only representative if it contains images similar to anything that can be encountered in future. For this reason a representative database may be very large and is not easy to build. In addition for testing purposes one needs multiple images of a large number of people, acquired over a period of time under different physical conditions representing the typical variations encountered in practice. Obviously this is a very slow process. Potentially the variation between the faces in the database can be large suggesting that the representation of all these different images in terms of eigenfaces may not be particularly efficient. One idea is to separate all the facial images into different, more or less homogeneous classes. Again this can only be done with access to a sufficiently large database, probably consisting of several thousand faces.
5
A, Anila H. "Synthesis of fluorescent probes for specific recognition and imaging applications." Thesis(Ph.D.), CSIR-National Chemical Laboratory, Pune, 2018. http://dspace.ncl.res.in:8080/xmlui/handle/20.500.12252/4271.
Full text
6
Brown, Georgina. "Considering accent recognition technology for forensic applications." Thesis, University of York, 2017. http://etheses.whiterose.ac.uk/20393/.
Full textAbstract:
Speaker recognition technology is becoming more available to forensic speech analysts to help to arrive at conclusions around how likely the speech in multiple recordings was produced by the same speaker. However, there is not currently a suitable technological tool that could assist with speaker profiling tasks (i.e. tasks where we wish to deduce information about an unknown speaker). Accent recognition technology could play a role in speaker profiling tasks. This thesis therefore presents numerous automatic accent recognition experiments that have been motivated by forensic applications. This thesis conducts a detailed examination of one automatic accent recognition system in particular, the York ACCDIST-based automatic accent recognition system (the Y-ACCDIST system). It is trained to assign an accent label to a speaker's speech sample. Unlike other accent recognition system architectures, Y-ACCDIST takes a segmental approach by forming models of speakers' accents using representations of individual phonemes. Implementing a segmentation phase comes at a practical cost, but it is expected that Y-ACCDIST's segmental approach captures a more detailed reflection of a speaker's accent than other accent recognition systems. When classifying speech samples into one of four categories, Y-ACCDIST achieved a recognition rate of 86.7% correct, while the best-performing text-independent system obtained 47.5%. This thesis also shows Y-ACCDIST's performance on spontaneous speech data. On a three-way classification task on Northern English accents, we witness a recognition rate of 86.7% correct. Additionally, we achieved 63.1% correct when classifying recordings into one of seven non-native English categories. The latter task is also a demonstration of Y-ACCDIST's capabilities on telephone data.
7
Aleixo, Patrícia Nunes. "Object detection and recognition for robotic applications." Master's thesis, Universidade de Aveiro, 2014. http://hdl.handle.net/10773/13811.
Full textAbstract:
Mestrado em Engenharia Eletrónica e TelecomunicaçõesThe computer vision assumes an important relevance in the development of robotic applications. In several applications, robots need to use vision to detect objects, a challenging and sometimes difficult task. This thesis is focused on the study and development of algorithms to be used in detection and identification of objects on digital images to be applied on robots that will be used in practice cases. Three problems are addressed: Detection and identification of decorative stones for textile industry; Detection of the ball in robotic soccer; Detection of objects in a service robot, that operates in a domestic environment. In each case, different methods are studied and applied, such as, Template Matching, Hough transform and visual descriptors (like SIFT and SURF). It was chosen the OpenCv library in order to use the data structures to image manipulation, as well as other structures for all information generated by the developed vision systems. Whenever possible, it was used the implementation of the described methods and have been developed new approaches, both in terms of pre-processing algorithms and in terms of modification of the source code in some used functions. Regarding the pre-processing algorithms, were used the Canny edge detector, contours detection, extraction of color information, among others. For the three problems, there are presented and discussed experimental results in order to evaluate the best method to apply in each case. The best method for each application is already integrated or in the process of integration in the described robots.
A visão por computador assume uma importante relevância no desenvolvimento de aplicações robóticas, na medida em que há robôs que precisam de usar a visão para detetar objetos, uma tarefa desafiadora e por vezes difícil. Esta dissertação foca-se no estudo e desenvolvimento de algoritmos para a deteção e identificação de objetos em imagem digital para aplicar em robôs que serão usados em casos práticos. São abordados três problemas: Deteção e identificação de pedras decorativas para a indústria têxtil; Deteção da bola em futebol robótico; Deteção de objetos num robô de serviço, que opera em ambiente doméstico. Para cada caso, diferentes métodos são estudados e aplicados, tais como, Template Matching, transformada de Hough e descritores visuais (como SIFT e SURF). Optou-se pela biblioteca OpenCv com vista a utilizar as suas estruturas de dados para manipulação de imagem, bem como as demais estruturas para toda a informação gerada pelos sistemas de visão desenvolvidos. Sempre que possivel utilizaram-se as implementações dos métodos descritos tendo sido desenvolvidas novas abordagens, quer em termos de algoritmos de preprocessamento quer em termos de alteração do código fonte das funções utilizadas. Como algoritmos de pre-processamento foram utilizados o detetor de arestas Canny, deteção de contornos, extração de informação de cor, entre outros. Para os três problemas, são apresentados e discutidos resultados experimentais, de forma a avaliar o melhor método a aplicar em cada caso. O melhor método em cada aplicação encontra-se já integrado ou em fase de integração dos robôs descritos.
8
PAOLANTI, MARINA. "Pattern Recognition for challenging Computer Vision Applications." Doctoral thesis, Università Politecnica delle Marche, 2018. http://hdl.handle.net/11566/252904.
Full textAbstract:
La Pattern Recognition è lo studio di come le macchine osservano l'ambiente, imparano a distinguere i pattern di interesse dal loro background e prendono decisioni valide e ragionevoli sulle categorie di modelli. Oggi l'applicazione degli algoritmi e delle tecniche di Pattern Recognition è trasversale. Con i recenti progressi nella computer vision, abbiamo la capacità di estrarre dati multimediali per ottenere informazioni preziose su ciò che sta accadendo nel mondo. Partendo da questa premessa, questa tesi affronta il tema dello sviluppo di sistemi di Pattern Recognition per applicazioni reali come la biologia, il retail, la sorveglianza, social media intelligence e i beni culturali. L'obiettivo principale è sviluppare applicazioni di computer vision in cui la Pattern Recognition è il nucleo centrale della loro
progettazione, a partire dai metodi generali, che possono essere sfruttati in più campi di ricerca, per poi passare a metodi e tecniche che affrontano problemi specifici. Di fronte a molti tipi di dati, come immagini, dati biologici e traiettorie, una difficoltà fondamentale è trovare rappresentazioni vettoriali rilevanti. Per la progettazione del sistema di riconoscimento dei modelli vengono eseguiti i seguenti passaggi: raccolta dati, estrazione delle caratteristiche, approccio di apprendimento personalizzato e analisi e valutazione comparativa. Per una valutazione completa delle prestazioni, è di grande importanza collezionare un dataset specifico perché i metodi di progettazione che sono adattati a un
problema non funzionano correttamente su altri tipi di problemi. I metodi su misura, adottati per lo sviluppo delle applicazioni proposte, hanno dimostrato di essere in grado di estrarre caratteristiche statistiche complesse e di imparare in modo efficiente le loro rappresentazioni, permettendogli di generalizzare bene attraverso una vasta gamma di compiti di visione computerizzata.Pattern Recognition is the study of how machines can observe the environment, learn to distinguish patterns of interest from their background, and make sound and reasonable decisions about the patterns categories. Nowadays, the application of Pattern Recognition algorithms and techniques is ubiquitous and transversal. With the recent advances in computer vision, we now have the ability to mine such massive visual data to obtain valuable insight about what is happening in the world. The availability of affordable and high resolution sensors (e.g., RGB-D cameras, microphones and scanners) and data sharing have resulted in huge repositories of digitized documents (text, speech, image and video). Starting from such a premise, this thesis addresses the topic of developing next generation Pattern Recognition systems for real applications such as Biology, Retail, Surveillance, Social Media Intelligence and Digital Cultural Heritage. The main goal is to develop computer vision applications in which Pattern Recognition is the key core in their design, starting from general methods, that can be exploited in more fields, and then passing to methods and techniques addressing specific problems. The privileged focus is on up-to-date applications of Pattern Recognition techniques to real-world problems, and on interdisciplinary research, experimental and/or theoretical studies yielding new insights that advance Pattern Recognition methods. The final ambition is to spur new research lines, especially within interdisciplinary research scenarios. Faced with many types of data, such as images, biological data and trajectories, a key difficulty was to nd relevant vectorial representations. While this problem had been often handled in an ad-hoc way by domain experts, it has proved useful to learn these representations directly from data, and Machine Learning algorithms, statistical methods and Deep Learning techniques have been particularly successful. The representations are then based on compositions of simple parameterized processing units, the depth coming from the large number of such compositions. It was desirable to develop new, efficient data representation or feature learning/indexing techniques, which can achieve promising performance in the related tasks. The overarching goal of this work consists of presenting a pipeline to select the model that best explains the given observations; nevertheless, it does not prioritize in memory and time complexity when matching models to observations. For the Pattern Recognition system design, the following steps are performed: data collection, features extraction, tailored learning approach and comparative analysis and assessment. The proposed applications open up a wealth of novel and important opportunities for the machine vision community. The newly dataset collected as well as the complex areas taken into exam, make the research challenging. In fact, it is crucial to evaluate the performance of state of the art methods to demonstrate their strength and weakness and help identify future research for designing more robust algorithms. For comprehensive performance evaluation, it is of great importance developing a library and benchmark to gauge the state of the art because the methods design that are tuned to a specic problem do not work properly on other problems. Furthermore, the dataset selection is needed from different application domains in order to offer the user the opportunity to prove the broad validity of methods. Intensive attention has been drawn to the exploration of tailored learning models and algorithms, and their extension to more application areas. The tailored methods, adopted for the development of the proposed applications, have shown to be capable of extracting complex statistical features and efficiently learning their representations, allowing it to generalize well across a wide variety of computer vision tasks, including image classication, text recognition and so on.
9
Hayes, William S. "Pattern recognition and signal detection in gene finding." Diss., Georgia Institute of Technology, 1998. http://hdl.handle.net/1853/25420.
Full text
10
Abbott, Kevin Toney. "Applications of algebraic geometry to object/image recognition." [College Station, Tex. : Texas A&M University, 2007. http://hdl.handle.net/1969.1/ETD-TAMU-1935.
Full text
11
Müller, J. J. "USB telephony interface device for speech recognition applications /." Link to the online version, 2005. http://hdl.handle.net/10019/1127.
Full text
12
Lari, Karim. "Applications of Hidden Markov Grammars to speech recognition." Thesis, University of Cambridge, 1990. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.358676.
Full text
13
Jaimovich, Javier. "Emotion recognition from physiological indicators for musical applications." Thesis, Queen's University Belfast, 2013. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.601785.
Full textAbstract:
This thesis investigates the emotional response of audiences to music via physiological indicators, with the goal of creating interfaces that use emotional stale for music control, specifically in performance scenarios via electrodermal and cardiovascular measures. In the past two decades, multiple disciplines have shown interest in studying the relationship between music, emotion, and its physiological manifestation. However, despite the increasing attention, the actual mechanisms on how music modulates human emotion and how this correlates with physiological changes are still not well understood. Therefore, this topic provides interesting challenges to determine if musical emotions can be measured from audiences in ecological environments via physiological signals, In order to address this, there are several questions that need to be resolved; including how to measure physiological indicators of emotion in concert environments, what level of shared responses and variance can be expected from public audiences, and how to assess the induction of musical emotions on listeners. In order to answer these questions, the wor\( in this thesis starts by measuring physiological indicators of emotion in music concerts, revealing high correlations between the physiology of performers and audience members, as well as associations between physiological changes and structural and acoustical features of the music. In order to assess fell emotion on listeners and how these are manifested via changes in physiology, a series of modular public listening experiments (Emotion in Motion) were implemented in Dublin and New York, collecting physiological data and self-report measures of emotion from over 4000 participants. Analysis of this database reveals a set of specific physiological indicators that show significant relationships with musically induced emotions. This thesis also contributes robust feature extraction tools for EDA and HR, and a methodology for synchronization of multimodal signals for musical performance research .
14
Thien, Theodore Lim Ann. "Lamina-based feature recognition and applications in manufacturing." Thesis, Heriot-Watt University, 2000. http://hdl.handle.net/10399/1114.
Full text
15
Lopez-Bonilla, Roman Ernesto. "Object recognition in three-dimensions for robotic applications." Thesis, University of Bradford, 1990. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.305752.
Full text
16
Padilla, Michael Thomas 1974. "Applications of missing feature theory to speaker recognition." Thesis, Massachusetts Institute of Technology, 2000. http://hdl.handle.net/1721.1/67165.
Full textAbstract:
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2000.Includes bibliographical references (p. 100-101).
An important problem in speaker recognition is the degradation that occurs when speaker models trained with speech from one type of channel are used to score speech from another type of channel, known as channel mismatch. This thesis investigates various channel compensation techniques and approaches from missing feature theory for improving Gaussian mixture model (GMM)-based speaker verification under this mismatch condition. Experiments are performed using a speech corpus consisting of "clean" training speech and "dirty" test speech equal to the clean speech corrupted by additive Gaussian noise. Channel compensation methods studied are cepstral mean subtraction, RASTA, and spectral subtraction. Approaches to missing feature theory include missing feature compensation, which removes corrupted features, and missing feature restoration which predicts such features from neighboring features in both frequency and time. These methods are investigated both individually and in combination. In particular, missing feature compensation combined with spectral subtraction in the discrete Fourier transform domain significantly improves GMM speaker verification accuracy and outperforms all other methods examined in this thesis, reducing the equal error rate by about 10% more than other methods over a SNR range of 5-25 dB. Moreover, this considerably outperforms a state-of-the-art GMM recognizer for the mismatch application that combines missing feature theory with spectral subtraction developed in a mel-filter energy domain. Finally, the concept of missing restoration is explored. A novel linear minimum mean-squared-error missing feature estimator is derived and applied to pure vowels as well as a clean/dirty verification trial. While it does not improve performance in the verification trial, a large SNR improvement for features estimated for the pure vowel case indicate promise in the application of this method.
by Michael Thomas Padilla.
S.M.
17
Muller, J. J. "USB telephony interface device for speech recognition applications." Thesis, Stellenbosch : University of Stellenbosch, 2005. http://hdl.handle.net/10019.1/2757.
Full textAbstract:
Thesis (MScEng (Electrical and Electronic Engineering))--University of Stellenbosch, 2005.Automatic speech recognition (ASR) systems are an attractive means for companies to deliver value added services with which to improve customer satisfaction. Such ASR systems require a telephony interface to connect the speech recognition application to the telephone system. Commercially available telephony interfaces are usually operating system specific, and therefore hardware device driver issues complicate the development of software applications for different platforms that require telephony access. The drivers and application programming interface (API) for telephony interfaces are often available only for the Microsoft Windows operating systems. This poses a problem, as many of the software tools used for speech recognition research and development operate only on Linux-based computers. These interfaces are also typically in PCI/ISA card format, which hinders physical portability of the device to another computer. A simple, cheaper and easier to use USB telephony interface device, offering cross-platform portability, was developed and presented, together with the necessary API.
18
Olsson, Lars Jonas. "Multisensory object recognition and tracking for robotic applications." Case Western Reserve University School of Graduate Studies / OhioLINK, 1995. http://rave.ohiolink.edu/etdc/view?acc_num=case1062772620.
Full text
19
Govender, Natasha. "Active object recognition for 2D and 3D applications." Doctoral thesis, University of Cape Town, 2015. http://hdl.handle.net/11427/16520.
Full textAbstract:
Includes bibliographical referencesActive object recognition provides a mechanism for selecting informative viewpoints to complete recognition tasks as quickly and accurately as possible. One can manipulate the position of the camera or the object of interest to obtain more useful information. This approach can improve the computational efficiency of the recognition task by only processing viewpoints selected based on the amount of relevant information they contain. Active object recognition methods are based around how to select the next best viewpoint and the integration of the extracted information. Most active recognition methods do not use local interest points which have been shown to work well in other recognition tasks and are tested on images containing a single object with no occlusions or clutter. In this thesis we investigate using local interest points (SIFT) in probabilistic and non-probabilistic settings for active single and multiple object and viewpoint/pose recognition. Test images used contain objects that are occluded and occur in significant clutter. Visually similar objects are also included in our dataset. Initially we introduce a non-probabilistic 3D active object recognition system which consists of a mechanism for selecting the next best viewpoint and an integration strategy to provide feedback to the system. A novel approach to weighting the uniqueness of features extracted is presented, using a vocabulary tree data structure. This process is then used to determine the next best viewpoint by selecting the one with the highest number of unique features. A Bayesian framework uses the modified statistics from the vocabulary structure to update the system's confidence in the identity of the object. New test images are only captured when the belief hypothesis is below a predefined threshold. This vocabulary tree method is tested against randomly selecting the next viewpoint and a state-of-the-art active object recognition method by Kootstra et al.. Our approach outperforms both methods by correctly recognizing more objects with less computational expense. This vocabulary tree method is extended for use in a probabilistic setting to improve the object recognition accuracy. We introduce Bayesian approaches for object recognition and object and pose recognition. Three likelihood models are introduced which incorporate various parameters and levels of complexity. The occlusion model, which includes geometric information and variables that cater for the background distribution and occlusion, correctly recognizes all objects on our challenging database. This probabilistic approach is further extended for recognizing multiple objects and poses in a test images. We show through experiments that this model can recognize multiple objects which occur in close proximity to distractor objects. Our viewpoint selection strategy is also extended to the multiple object application and performs well when compared to randomly selecting the next viewpoint, the activation model and mutual information. We also study the impact of using active vision for shape recognition. Fourier descriptors are used as input to our shape recognition system with mutual information as the active vision component. We build multinomial and Gaussian distributions using this information, which correctly recognizes a sequence of objects. We demonstrate the effectiveness of active vision in object recognition systems. We show that even in different recognition applications using different low level inputs, incorporating active vision improves the overall accuracy and decreases the computational expense of object recognition systems.
20
Smith, Joshua E. "Selective molecular recognition conjugated nanoparticles for biological applications." [Gainesville, Fla.] : University of Florida, 2007. http://purl.fcla.edu/fcla/etd/UFE0021266.
Full text
21
Prendergast, David Jeremy. "Applications of statistical pattern recognition in medical imaging." Thesis, University of Manchester, 1993. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.629772.
Full text
22
Curado, Manuel. "Structural Similarity: Applications to Object Recognition and Clustering." Doctoral thesis, Universidad de Alicante, 2018. http://hdl.handle.net/10045/98110.
Full textAbstract:
In this thesis, we propose many developments in the context of Structural Similarity. We address both node (local) similarity and graph (global) similarity. Concerning node similarity, we focus on improving the diffusive process leading to compute this similarity (e.g. Commute Times) by means of modifying or rewiring the structure of the graph (Graph Densification), although some advances in Laplacian-based ranking are also included in this document. Graph Densification is a particular case of what we call graph rewiring, i.e. a novel field (similar to image processing) where input graphs are rewired to be better conditioned for the subsequent pattern recognition tasks (e.g. clustering). In the thesis, we contribute with an scalable an effective method driven by Dirichlet processes. We propose both a completely unsupervised and a semi-supervised approach for Dirichlet densification. We also contribute with new random walkers (Return Random Walks) that are useful structural filters as well as asymmetry detectors in directed brain networks used to make early predictions of Alzheimer's disease (AD). Graph similarity is addressed by means of designing structural information channels as a means of measuring the Mutual Information between graphs. To this end, we first embed the graphs by means of Commute Times. Commute times embeddings have good properties for Delaunay triangulations (the typical representation for Graph Matching in computer vision). This means that these embeddings can act as encoders in the channel as well as decoders (since they are invertible). Consequently, structural noise can be modelled by the deformation introduced in one of the manifolds to fit the other one. This methodology leads to a very high discriminative similarity measure, since the Mutual Information is measured on the manifolds (vectorial domain) through copulas and bypass entropy estimators. This is consistent with the methodology of decoupling the measurement of graph similarity in two steps: a) linearizing the Quadratic Assignment Problem (QAP) by means of the embedding trick, and b) measuring similarity in vector spaces. The QAP problem is also investigated in this thesis. More precisely, we analyze the behaviour of $m$-best Graph Matching methods. These methods usually start by a couple of best solutions and then expand locally the search space by excluding previous clamped variables. The next variable to clamp is usually selected randomly, but we show that this reduces the performance when structural noise arises (outliers). Alternatively, we propose several heuristics for spanning the search space and evaluate all of them, showing that they are usually better than random selection. These heuristics are particularly interesting because they exploit the structure of the affinity matrix. Efficiency is improved as well. Concerning the application domains explored in this thesis we focus on object recognition (graph similarity), clustering (rewiring), compression/decompression of graphs (links with Extremal Graph Theory), 3D shape simplification (sparsification) and early prediction of AD.Ministerio de Economía, Industria y Competitividad (Referencia TIN2012-32839 BES-2013-064482)
23
De, Rosa Mattia. "New methods, techniques and applications for sketch recognition." Doctoral thesis, Universita degli studi di Salerno, 2014. http://hdl.handle.net/10556/1460.
Full textAbstract:
2012-2013The use of diagrams is common in various disciplines. Typical examples include maps, line graphs, bar charts, engineering blueprints, architects’ sketches, hand drawn schematics, etc.. In general, diagrams can be created either by using pen and paper, or by using specific computer programs. These programs provide functions to facilitate the creation of the diagram, such as copy-and-paste, but the classic WIMP interfaces they use are unnatural when compared to pen and paper. Indeed, it is not rare that a designer prefers to use pen and paper at the beginning of the design, and then transfer the diagram to the computer later. To avoid this double step, a solution is to allow users to sketch directly on the computer. This requires both specific hardware and sketch recognition based software. As regards hardware, many pen/touch based devices such as tablets, smartphones, interactive boards and tables, etc. are available today, also at reasonable costs. Sketch recognition is needed when the sketch must be processed and not considered as a simple image and it is crucial to the success of this new modality of interaction. It is a difficult problem due to the inherent imprecision and ambiguity of a freehand drawing and to the many domains of applications. The aim of this thesis is to propose new methods and applications regarding the sketch recognition. The presentation of the results is divided into several contributions, facing problems such as corner detection, sketched symbol recognition and autocompletion, graphical context detection, sketched Euler diagram interpretation. The first contribution regards the problem of detecting the corners present in a stroke. Corner detection is often performed during preprocessing to segment a stroke in single simple geometric primitives such as lines or curves. The corner recognizer proposed in this thesis, RankFrag, is inspired by the method proposed by Ouyang and Davis in 2011 and improves the accuracy percentages compared to other methods recently proposed in the literature. The second contribution is a new method to recognize multi-stroke hand drawn symbols, which is invariant with respect to scaling and supports symbol recognition independently from the number and order of strokes. The method is an adaptation of the algorithm proposed by Belongie et al. in 2002 to the case of sketched images. This is achieved by using stroke related information. The method has been evaluated on a set of more than 100 symbols from the Military Course of Action domain and the results show that the new recognizer outperforms the original one. The third contribution is a new method for recognizing multi-stroke partially hand drawn symbols which is invariant with respect to scale, and supports symbol recognition independently from the number and order of strokes. The recognition technique is based on subgraph isomorphism and exploits a novel spatial descriptor, based on polar histograms, to represent relations between two stroke primitives. The tests show that the approach gives a satisfactory recognition rate with partially drawn symbols, also with a very low level of drawing completion, and outperforms the existing approaches proposed in the literature. Furthermore, as an application, a system presenting a user interface to draw symbols and implementing the proposed autocompletion approach has been developed. Moreover a user study aimed at evaluating the human performance in hand drawn symbol autocompletion has been presented. Using the set of symbols from the Military Course of Action domain, the user study evaluates the conditions under which the users are willing to exploit the autocompletion functionality and those under which they can use it efficiently. The results show that the autocompletion functionality can be used in a profitable way, with a drawing time saving of about 18%. The fourth contribution regards the detection of the graphical context of hand drawn symbols, and in particular, the development of an approach for identifying attachment areas on sketched symbols. In the field of syntactic recognition of hand drawn visual languages, the recognition of the relations among graphical symbols is one of the first important tasks to be accomplished and is usually reduced to recognize the attachment areas of each symbol and the relations among them. The approach is independent from the method used to recognize symbols and assumes that the symbol has already been recognized. The approach is evaluated through a user study aimed at comparing the attachment areas detected by the system to those devised by the users. The results show that the system can identify attachment areas with a reasonable accuracy. The last contribution is EulerSketch, an interactive system for the sketching and interpretation of Euler diagrams (EDs). The interpretation of a hand drawn ED produces two types of text encodings of the ED topology called static code and ordered Gauss paragraph (OGP) code, and a further encoding of its regions. Given the topology of an ED expressed through static or OGP code, EulerSketch automatically generates a new topologically equivalent ED in its graphical representation. [edited by author]
XII n.s.
24
Rezazadegan, Fahimeh. "Human action recognition and prediction for robotics applications." Thesis, Queensland University of Technology, 2019. https://eprints.qut.edu.au/127283/1/__qut.edu.au_Documents_StaffHome_StaffGroupH%24_halla_Desktop_Fahimeh_Rezazadegan_Thesis.pdf.
Full textAbstract:
This study is a step forward in developing two different methods; one recognises human actions in an unbiased environment, the other predicts the next human action. The proposed methods that are based on deep learning, convolutional neural networks and long-short term memories, work regardless of camera motion, viewpoint variation, and irrelevant background context. The key outcome of this research is to enable an assistive robot to help a human peer performing an assembly task, using the proposed algorithms.
25
Ma, Chengyuan. "A detection-based pattern recognition framework and its applications." Diss., Georgia Institute of Technology, 2010. http://hdl.handle.net/1853/33889.
Full textAbstract:
The objective of this dissertation is to present a detection-based pattern recognition framework and demonstrate its applications in automatic speech recognition and broadcast news video story segmentation.
Inspired by the studies of modern cognitive psychology and real-world pattern recognition systems, a detection-based pattern recognition framework is proposed to provide an alternative solution for some complicated pattern recognition problems. The primitive features are first detected and the task-specific knowledge hierarchy is constructed level by level; then a variety of heterogeneous information sources are combined together and the high-level context is incorporated as additional information at certain stages.
A detection-based framework is a â divide-and-conquerâ design paradigm for pattern recognition problems, which will decompose a conceptually difficult problem into many elementary sub-problems that can be handled directly and reliably. Some information fusion strategies will be employed to integrate the evidence from a lower level to form the evidence at a higher level. Such a fusion procedure continues until reaching the top level. Generally, a detection-based framework has many advantages: (1) more flexibility in both detector design and fusion strategies, as these two parts
can be optimized separately; (2) parallel and distributed computational components in primitive feature detection. In such a component-based framework, any primitive component can be replaced by a new one while other components remain unchanged; (3) incremental information integration; (4) high level context information as additional information sources, which can be combined with bottom-up processing at any stage.
This dissertation presents the basic principles, criteria, and techniques for detector design and hypothesis verification based on the statistical detection and decision theory. In addition, evidence fusion strategies were investigated in this dissertation. Several novel detection algorithms and evidence fusion methods were proposed and their effectiveness was justified in automatic speech recognition and broadcast news video segmentation system. We believe such a detection-based framework can be employed
in more applications in the future.
26
Evans, Fiona H. "Syntactic models with applications in image analysis /." [Perth, W.A.] : [University of W.A.], 2006. http://theses.library.uwa.edu.au/adt-WU2007.0001.
Full text
27
Breedt, Morne. "Integrating biometric authentication into multiple applications." Diss., University of Pretoria, 2005. http://hdl.handle.net/2263/27605.
Full textAbstract:
The Internet has grown from its modest academic beginnings into an important, global communication medium. It has become a significant, intrinsic part of our lives, how we distribute information and how we transact. It is used for a variety of purposes, including: banking; home shopping; commercial trade - using EDI (Electronic Data Interchange); and to gather information for market research and other activities. Owing to its academic origins, the early developers of the Internet did not focus on security. However, now that it has rapidly evolved into an extensively used, global commercial transaction and distribution channel, security has become a big concern. Fortunately, the field of information security has started to evolve in response and is fast becoming an important discipline with a sound theoretical basis. The discipline views the twin processes of identification and authentication as crucial aspects of information security. An individual access attempt must be identifiable prior to access being authorised otherwise system confidentiality cannot be enforced nor integrity safeguarded. Similarly, non-denial becomes impossible to instigate since the system is unable to log an identity against specific transactions. Consequently, identification and authentication should always be viewed as the first step to successfully enforcing information security. The process of identification and authorisation is, in essence, the ability to prove or verify an identity. This is usually accomplished using either one or a combination of the following three traditional identification techniques: something you possess; something you know; or something you are. A critical consideration when designing an application is which identification method, or combination of methods, from the three described above to use. Each method offers its own pros and cons and there are many ways to compare and contrast them. The comparison made in this study identifies biometrics as the best solution in a distributed application environment. There are, however, two over-arching hindrances to its widespread adoption. The first is the environment’s complexity - with multiple applications being accessed by both the public and the private sectors - and the second is that not all biometrics are popular and no single method has universe appeal. The more significant hindrance of the two is the latter, that of acceptance and trust, because it matters little how good or efficient a system is if nobody is willing to use it. This observation suggests that the identification system needs to be made as flexible as possible. In a democratic society, it could be argued that the best way of ensuring the successful adoption of a biometric system would be to allow maximum freedom of choice and let users decide which biometric method they would like to use. Although this approach is likely to go a long way towards solving the acceptance issue, it increases the complexity of the environment significantly. This study attempts to solve this problem by reducing the environment’s complexity while simultaneously ensuring the user retains maximum biometric freedom of choice. This can be achieved by creating a number of central biometric repositories. Each repository would be responsible for maintaining a biometric template data store for a type of biometric. These repositories or “Biometric Authorities” would act as authentication facilitators for a wide variety of applications and free them from that responsibility.Dissertation (MSc (Computer Engineering))--University of Pretoria, 2007.
Electrical, Electronic and Computer Engineering
MSc
unrestricted
28
Hozatli, Aykut. "3d Object Recognition By Geometric Hashing For Robotics Applications." Master's thesis, METU, 2009. http://etd.lib.metu.edu.tr/upload/12610434/index.pdf.
Full textAbstract:
The main aim of 3D Object recognition is to recognize objects under translation
and rotation. Geometric Hashing is one of the methods which represents a
rotation and translation invariant approach and provides indexing of structural
features of the objects in an efficient way. In this thesis, Geometric Hashing is
used to store the geometric relationship between discriminative surface
properties which are based on surface curvature. In this thesis surface is
represented by shape index and splash where shape index defines particular
shaped surfaces and splash introduces topological information. The method is
tested on 3D object databases and compared with other methods in the
literature.
29
Rönnqvist, Patrik. "Surveillance Applications : Image Recognition on the Internet of Things." Thesis, Mittuniversitetet, Institutionen för informationsteknologi och medier, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-18557.
Full textAbstract:
This is a B.Sc. thesis within the Computer Science programme at the Mid Sweden University. The purpose of this project has been to investigate the possibility of using image based surveillance in smart applications on the Internet-of-Things. The goals involved investigating relevant technologies and designing, implementing and evaluating an application that can perform image recognition. A number of image recognition techniques have been investigated and the use of color histograms has been chosen for its simplicity and low resource requirement. The main source of study material has been the Internet. The solution has been developed in the Java programming language, for use on the Android operating system and using the MediaSense platform for communication. It consists of a camera application that produces image data and a monitor application that performs image recognition and handles user interaction. To evaluate the solution a number of tests have been performed and its pros and cons have been identified. The results show that the solution can differentiate between simple colored stick figures in a controlled environment. Variables such as lighting and the background are significant. The application can reliably send images from the camera to the monitor at a rate of one image every four seconds. The possibility of using streaming video instead of images has been investigated but found to be difficult under the given circumstances. It has been concluded that while the solution cannot differentiate between actual people it has shown that image based surveillance is possible on the IoT and the goals of this project have been satisfied. The results were expected and hold little newsworthiness. Suggested future work involves improvements to the MediaSense platform and infrastructure for processing and storing data.MediaSense
30
Bobak, Anna Katarzyna. "Theoretical and real-world applications of superior face recognition." Thesis, Bournemouth University, 2016. http://eprints.bournemouth.ac.uk/25015/.
Full textAbstract:
While previous work has identified the existence of people with extraordinary face recognition skills (so-called “super-recognisers”; SRs), the cognitive and perceptual underpinnings of the ability are unknown. This thesis addresses this issue, using behavioural and eye-movement measures. It also evaluates the methods used to identify SRs, their role in more applied national security settings, and ways of improving face recognition in typical perceivers. The first set of studies offers an in-depth cognitive and perceptual examination of six SRs using a case-series approach. This investigation revealed that while SRs are a heterogeneous group, they consistently show enhanced holistic processing. A second set of studies examined the eye-movements of SRs in a standard face memory task and a more ecologically valid free-viewing task. In both experiments SRs spent more time looking at the nose (i.e. the centre of faces) than typical perceivers, countering previous work that suggests the eye region is critical in facial identification. A subsequent study was aimed at establishing the UK-specific norms for dominant tests of face recognition and face perception, using a large sample of young British adults. Results suggested that females are better at face recognition than males, and that country-specific control norms are needed for these neuropsychological tests. A fourth set of studies looked at the performance of SRs on more applied face recognition tasks, replicating face matching and recognition scenarios. Results strongly suggested that some SRs are best-suited to particular tasks, and when identified correctly would make extremely valuable employees in national security settings. A final study examined if face matching and face recognition skills can be improved in typical perceivers via intranasal inhalation of the nonapeptide oxytocin, yet neither process was improved following this intervention. The theoretical and practical implications resulting from all these vi investigations are discussed, particularly in relation to our understanding of the typical face-processing system, and in making practical recommendations for the implementation of super recognition in national security settings.
31
Nopsuwanchai, Roongroj. "Discriminative training methods and their applications to handwriting recognition." Thesis, University of Cambridge, 2004. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.616183.
Full text
32
甄榮輝 and Wing-fai Yan. "Eye movement measurement for clinical applications using pattern recognition." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 1988. http://hub.hku.hk/bib/B31209026.
Full text
33
MOREIRA, GUSTAVO COSTA GOMES. "OBJECT RECOGNITION SYSTEM IN DIGITAL VIDEOS FOR INTERACTIVE APPLICATIONS." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2008. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=13069@1.
Full textAbstract:
COORDENAÇÃO DE APERFEIÇOAMENTO DO PESSOAL DE ENSINO SUPERIORDetecção e reconhecimento de objetos são uma questão importante na área de Visão Computacional, onde a sua realização em tempo real e com taxas baixas de falsos positivos tem se tornado o objetivo principal de inúmeras pesquisas, inclusive daquelas relacionadas às novas formas de interatividade na TV Digital. Esta dissertação propõe um sistema de software baseado em aprendizado de máquina que permite um treinamento eficiente para novos objetos e realiza o subseqüente reconhecimento destes objetos em tempo real, tanto para imagens estáticas como para vídeos digitais. O sistema é baseado no uso de características Haar do objeto, que requerem um baixo tempo de computação para o seu cálculo, e na utilização de classificadores em cascata, que permitem tanto um rápido descarte de áreas da imagem que não possuem o objeto de interesse, quanto uma baixa ocorrência de falsos positivos. Por meio do uso de técnicas de segmentação de imagem, o sistema torna a busca por objetos uma operação extremamente rápida em vídeos de alta resolução. Além disto, com a utilização de técnicas de paralelismo, pode-se detectar vários objetos simultaneamente sem perda de desempenho.
Object detection and recognition are an important issue in the field of Computer Vision, where its accomplishment in both real time and low false positives rates has became the main goal of various research works, including the ones related to new interactivity forms in Digital TV. This dissertation proposes a software system based on machine learning that allows an efficient training for new objects and performs their subsequent recognition in real time, for both static images and digital videos. The proposed system is based on the use of Haar features of the object, which require a low computation time for their calculation, and on the usage of a cascade of classifiers, which allows a quick discard of image areas that does not contain the desired object while having a low occurrence of false positives. Through the use of image segmentation techniques, the system turns the search for objects into an extremely fast operation in high-resolution videos. Furthermore, through the use of parallelism techniques, one can simultaneously detect various objects without losing performance.
34
Jan, Asim. "Deep learning based facial expression recognition and its applications." Thesis, Brunel University, 2017. http://bura.brunel.ac.uk/handle/2438/15944.
Full textAbstract:
Facial expression recognition (FER) is a research area that consists of classifying the human emotions through the expressions on their face. It can be used in applications such as biometric security, intelligent human-computer interaction, robotics, and clinical medicine for autism, depression, pain and mental health problems. This dissertation investigates the advanced technologies for facial expression analysis and develops the artificial intelligent systems for practical applications. The first part of this work applies geometric and texture domain feature extractors along with various machine learning techniques to improve FER. Advanced 2D and 3D facial processing techniques such as Edge Oriented Histograms (EOH) and Facial Mesh Distances (FMD) are then fused together using a framework designed to investigate their individual and combined domain performances. Following these tests, the face is then broken down into facial parts using advanced facial alignment and localising techniques. Deep learning in the form of Convolutional Neural Networks (CNNs) is also explored also FER. A novel approach is used for the deep network architecture design, to learn the facial parts jointly, showing an improvement over using the whole face. Joint Bayesian is also adapted in the form of metric learning, to work with deep feature representations of the facial parts. This provides a further improvement over using the deep network alone. Dynamic emotion content is explored as a solution to provide richer information than still images. The motion occurring across the content is initially captured using the Motion History Histogram descriptor (MHH) and is critically evaluated. Based on this observation, several improvements are proposed through extensions such as Average Spatial Pooling Multi-scale Motion History Histogram (ASMMHH). This extension adds two modifications, first is to view the content in different spatial dimensions through spatial pooling; influenced by the structure of CNNs. The other modification is to capture motion at different speeds. Combined, they have provided better performance over MHH, and other popular techniques like Local Binary Patterns - Three Orthogonal Planes (LBP-TOP). Finally, the dynamic emotion content is observed in the feature space, with sequences of images represented as sequences of extracted features. A novel technique called Facial Dynamic History Histogram (FDHH) is developed to capture patterns of variations within the sequence of features; an approach not seen before. FDHH is applied in an end to end framework for applications in Depression analysis and evaluating the induced emotions through a large set of video clips from various movies. With the combination of deep learning techniques and FDHH, state-of-the-art results are achieved for Depression analysis.
35
Glass, James Robert. "Finding acoustic regularities in speech : applications to phonetic recognition." Thesis, Massachusetts Institute of Technology, 1988. http://hdl.handle.net/1721.1/14777.
Full text
36
Gellatly, Andrew William. "The Use of Speech Recognition Technology in Automotive Applications." Diss., Virginia Tech, 1997. http://hdl.handle.net/10919/30373.
Full textAbstract:
The research objectives were (1) to perform a detailed
review of the literature on speech recognition technology
and the attentional demands of driving; (2) to develop
decision tools that assist designers of in-vehicle systems;
(3) to experimentally examine automatic speech recognition
(ASR) design parameters, input modalities, and driver
ages; and (4) to provide human factors recommendations
for the use of speech recognition technology in automotive
applications. Two experiments were conducted to
determine the effects of ASR design parameters, input
modality, and age on driving performance, system usability,
and driver preference/acceptance. Eye movement
behavior, steering input behavior, speed maintenance
behavior, reaction time to forward scene event, task
completion time, and task completion errors when driving
and performing in-vehicle tasks were measured. Driver
preference/acceptance subjective data were also recorded.
The results showed that ASR design parameters
significantly affected measures of driving performance,
system usability, and driver preference/acceptance.
However, from a practical viewpoint, ASR design
parameters had a nominal effect on driving performance.
Differences measured in driving performance brought on by
changes in ASR system design parameters were small
enough that alternative ASR system designs could be
considered without impacting driving performance. No
benefits could be claimed for ASR systems improving
driving safety/performance compared to current
manual-control systems. Speech recognition system design
demonstrated a moderate influence on the usability of
in-vehicle tasks. Criteria such as task completion times and
task completion errors were shown to be different between
speech-input and manual-input control methods, and under
different ASR design configurations. Therefore, trade-offs
between ASR system designs, and between speech-input
and manual-input systems, could be evaluated in terms of
usability. Finally, ASR system design had a nominal effect
on driver preference/acceptance. Further research is
warranted to determine if long-term use of ASR systems
with less than optimal design parameters would result in
significantly lower values for driver preference/acceptance
compared to data collected in this research effort. Human
factors recommendations for the use of ASR technology in
automotive applications are included. The
recommendations are based on the empirical research and
the literature review on speech recognition technology and
the attentional demands of driving.Ph. D.
37
Bastas, Selin A. "Nocturnal Bird Call Recognition System for Wind Farm Applications." University of Toledo / OhioLINK, 2012. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1325803309.
Full text
38
Yan, Wing-fai. "Eye movement measurement for clinical applications using pattern recognition /." [Hong Kong : University of Hong Kong], 1988. http://sunzi.lib.hku.hk/hkuto/record.jsp?B12434024.
Full text
39
Xian, Cory Jianke. "Novel applications of the complementary peptide molecular recognition approach." Thesis, Xian, Cory Jianke (1992) Novel applications of the complementary peptide molecular recognition approach. PhD thesis, Murdoch University, 1992. https://researchrepository.murdoch.edu.au/id/eprint/51713/.
Full textAbstract:
Previous studies have demonstrated that the complementary peptide (CP) recognition approach can be a successful strategy in studying ligand and receptor interactions. A CP or antisense peptide can be designed in two ways: (1) decoding the complementary or antisense DNA of a ligand; (2) hydropathic anti-complementation through a computer programme from the amino acid sequence of the ligand (CG-CP). Previous work has shown (1) specific binding between a CP and its sense ligand; (2) recognition of the receptor for the ligand by an anti-CP antibody; (3) the idiotype-anti-idiotype relationship between the anti-ligand and anti-CP antibodies; and (4) Prediction and demonstration of previously unknown binding sites or interacting proteins.
The work described in this thesis involves the use of the CP approach to novel applications.
New Type of Affinity Column.
Previous workers have experienced failure or extreme difficulties in various conventional attempts to isolate the 21.5 KD myelin basic protein (MBP) from its other isoforms. Several CPs were constructed according to different methods to 21.5 KD MBP exon II, which is not present in the other isoform of sheep MBP. One of the CPs, CG-CP, was shown to be capable of binding the exon II sense peptide with a high affinity in an ELISA binding assay. A CG-CP column was generated in attempts to isolate the 21.5 KD MBP. Results showed that the column could significantly enrich this isoform from a crude MBP preparation, examined by SDS-PAGE and Western blotting analyses. But there was also some non-specific adsorption of MBP to column matrix, as observed by previous workers with conventional columns.
Mimics of Antibody Combining Sites.
Previous studies have reported that CPs can be used to generate anti-idiotypic antibodies (anti-ID) (ie., antibodies against an antibody). Several CPs were designed to the anti-human MBP monoclonal antibody (Mab 65) epitope on MBP. ELISA binding assays illustrated specific binding of soluble MBP to the pre-coated CPs (particularly the 3’-5’CP); on the other hand, the soluble CPs did not bind to the pre-coated MBP. An antibody to the 3’-5’CP was generated; but this antibody did not show any anti-ID relation to the Mab 65.
Investigation on the ID-anti-ID relationship between the two antibodies raised with the 21.5 KD MBP exon II sense peptide and its 5’-3’CP was also carried out, but results confirmed the finding with the Mab 65 case.
T Cell Receptors (TCRs) in Autoimmune Diseases.
Experimental autoimmune encephalomyelitis (EAE) is the most widely studied experimental autoimmune disease. A CP (EAE CP) was designed to the EAE epitope (rat MBP 72-82) and it was found that this EAE CP had sequence similarities to TCR, MHC II and LEA molecules in a PIR protein database search. A rabbit antibody to EAE CP was generated and used as an indicator for the interaction between the CP and epitope peptides in an ELISA binding assay, which demonstrated specific and high-affinity binding of EAE CP to the epitope peptides. This anti-EAE CP was also shown to be able to stain rat peripheral blood lymphocytes in an in situ cellular ELISA although not to the EAE specific T cell line in a flow cytometry analysis. A rat TCR. Vp peptide that was used to prevent and treat EAE by others had sequence similarity to the EAE CP, thus the latter was also used in attempts to down-regulate EAE, with results showing that the EAE CP could marginally (but not significantly) delay the onset and reduce the severity of EAE.
Sense-antisense complementarity analysis was conducted between interactive yd TCRs and the Adjuvant arthritogenic heat-shock peptides. Results showed that complementaritiescould be observed but tended to be non-specific.
Based on the sequence homologies between the receptor complements and ligands, the CP approach was also used to in attempts to predict the antigen(s) possibly involved in multiple sclerosis (MS). CPs to γ TCR sequences from a MS patient and a control designed and used as query sequences to do protein database searches. Some viruses were matched, which had been suggested to be involved in MS by others; but no viruses were consistently matched to all of the MS γ TCR CP sequences. No myelin or other relevant brain proteins were matched.
HIV-1 and Receptors.
CPs were constructed to HIV-1 gp120 receptor binding region and gp41 fusion peptide, and were found to have sequence similarities respectively to CD4 (a known receptor for HIV) and LFA-1 (suggested to be a possible second receptor by others). Attempts were made to block HIV-1 infectivity with these CP-gp120 and CP-gp41, but with negative results. Specific antibodies to both CPs were also produced but were shown not to be able to stain the human peripheral blood lymphocytes in both in situ cellular ELIS As and How cytometry analyses. The anti-CPgpl20 did not cross-react to the recombinant human CD4.
Cytokines and Receptors.
CPs to potential receptor binding sites on GM-CSF, IL-3, and IL-5 were designed and were shown to have interesting sequence homologies to their receptor sequences by the BESTFIT sequence analyses. Results with two CPs of GM-CSF (20- 28 and 18-25) indicated that these CPs and an anti-CP-GMCSF18-25 antiserum could not inhibit the GM-CSF binding to GM-CSF high-affinity receptor and that an anti-CP-GMCSF20- 28 antiserum could not stain granulocytes and monocytes.
In summary, sense-antisense sequence complementarity (or sequence homology between the sense receptor and the antisense ligand) was observed in the various systems studied. Sense-antisense peptide interaction was demonstrated in several cases examined including (1) EAE epitope peptides and EAE CP; (2) 21.5 KD MBP exon II peptide or whole 21.5 KD MBP and exon II CPs (particularly CG-CP); (3) MBP and the anti-MBP Mab 65 epitope CPs. The interaction between the exon II CG-CP and exon II peptide was successfully utilized to enrich the 21.5 KD MBP from the crude MBP preparation through a CG-CP affinity column. However, no success was achieved in recognizing the receptors for the ligands by using the anti-ligand CP antibodies in the various systems examined (HIV receptor, GMCSF receptor, 21.5 KD MBP interacting protein and EAE specific TCR or MHC II molecules), and in using CPs as biological antagonists (eg., Mab 65-MBP recognition inhibition, EAE prevention, HIV infection inhibition, and cytokine-receptor binding blocking), in contrast to previous workers’ success with peptide hormones. Furthermore, Whitaker’s success in generating anti-ID antibodies by MBP CPs could not be reproduced with two other regions on MBP (exon II and Mab 65 epitope in exon 6).
In conclusion, therefore, specific sense-antisense peptide interaction of the CP approach (particularly the CG-CP approach) offers a promising potential for isolating or enriching proteins or peptides; however this CP approach is not universally applicable, especially in designing biological antagonists and generating anti-receptor or anti-ID antibodies with the protein/protein systems of complex structures such as HIV/receptors, cytokines/receptors, epitope/TCR, and MBP/antibodies, in contrast to some peptide hormone/receptor systems.
40
Gurrapu, Chaitanya. "Human Action Recognition In Video Data For Surveillance Applications." Thesis, Queensland University of Technology, 2004. https://eprints.qut.edu.au/15878/1/Chaitanya_Gurrapu_Thesis.pdf.
Full textAbstract:
Detecting human actions using a camera has many possible applications in the security industry. When a human performs an action, his/her body goes through a signature sequence of poses. To detect these pose changes and hence the activities performed, a pattern recogniser needs to be built into the video system. Due to the temporal nature of the patterns, Hidden Markov Models (HMM), used extensively in speech recognition, were investigated. Initially a gesture recognition system was built using novel features. These features were obtained by approximating the contour of the foreground object with a polygon and extracting the polygon's vertices. A Gaussian Mixture Model (GMM) was fit to the vertices obtained from a few frames and the parameters of the GMM itself were used as features for the HMM.
A more practical activity detection system using a more sophisticated foreground segmentation algorithm immune to varying lighting conditions and permanent changes to the foreground was then built. The foreground segmentation algorithm models each of the pixel values using clusters and continually uses incoming pixels to update the cluster parameters. Cast shadows were identified and removed by assuming that shadow regions were less likely to produce strong edges in the image than real objects and that this likelihood further decreases after colour segmentation. Colour segmentation itself was performed by clustering together pixel values in the feature space using a gradient ascent algorithm called mean shift. More robust features in the form of mesh features were also obtained by dividing the bounding box of the binarised object into grid elements and calculating the ratio of foreground to background pixels in each of the grid elements. These features were vector quantized to reduce their dimensionality and the resulting symbols presented as features to the HMM to achieve a recognition rate of 62% for an event involving a person writing on a white board. The recognition rate increased to 80% for the "seen" person sequences, i.e. the sequences of the person used to train the models. With a fixed lighting position, the lack of a shadow removal subsystem improved the detection rate. This is because of the consistent profile of the shadows in both the training and testing sequences due to the fixed lighting positions. Even with a lower recognition rate, the shadow removal subsystem was considered an indispensable part of a practical, generic surveillance system.
41
Gurrapu, Chaitanya. "Human Action Recognition In Video Data For Surveillance Applications." Queensland University of Technology, 2004. http://eprints.qut.edu.au/15878/.
Full textAbstract:
Detecting human actions using a camera has many possible applications in the security industry. When a human performs an action, his/her body goes through a signature sequence of poses. To detect these pose changes and hence the activities performed, a pattern recogniser needs to be built into the video system. Due to the temporal nature of the patterns, Hidden Markov Models (HMM), used extensively in speech recognition, were investigated. Initially a gesture recognition system was built using novel features. These features were obtained by approximating the contour of the foreground object with a polygon and extracting the polygon's vertices. A Gaussian Mixture Model (GMM) was fit to the vertices obtained from a few frames and the parameters of the GMM itself were used as features for the HMM. A more practical activity detection system using a more sophisticated foreground segmentation algorithm immune to varying lighting conditions and permanent changes to the foreground was then built. The foreground segmentation algorithm models each of the pixel values using clusters and continually uses incoming pixels to update the cluster parameters. Cast shadows were identified and removed by assuming that shadow regions were less likely to produce strong edges in the image than real objects and that this likelihood further decreases after colour segmentation. Colour segmentation itself was performed by clustering together pixel values in the feature space using a gradient ascent algorithm called mean shift. More robust features in the form of mesh features were also obtained by dividing the bounding box of the binarised object into grid elements and calculating the ratio of foreground to background pixels in each of the grid elements. These features were vector quantized to reduce their dimensionality and the resulting symbols presented as features to the HMM to achieve a recognition rate of 62% for an event involving a person writing on a white board. The recognition rate increased to 80% for the "seen" person sequences, i.e. the sequences of the person used to train the models. With a fixed lighting position, the lack of a shadow removal subsystem improved the detection rate. This is because of the consistent profile of the shadows in both the training and testing sequences due to the fixed lighting positions. Even with a lower recognition rate, the shadow removal subsystem was considered an indispensable part of a practical, generic surveillance system.
42
Savkov, Aleksandar Dimitrov. "Deciphering clinical text : concept recognition in primary care text notes." Thesis, University of Sussex, 2017. http://sro.sussex.ac.uk/id/eprint/68232/.
Full textAbstract:
Electronic patient records, containing data about the health and care of a patient, are a valuable source of information for longitudinal clinical studies. The General Practice Research Database (GPRD) has collected patient records from UK primary care practices since the late 1980s. These records contain both structured data (in the form of codes and numeric values) and free text notes. While the structured data have been used extensively in clinical studies, there are significant practical obstacles in extracting information from the free text notes. The main obstacles are data access restrictions, due to the presence of sensitive information, and the specific language of medical practitioners, which renders standard language processing tools ineffective. The aim of this research is to investigate approaches for computer analysis of free text notes. The research involved designing a primary care text corpus (the Harvey Corpus) annotated with syntactic chunks and clinically-relevant semantic entities, developing a statistical chunking model, and devising a novel method for applying machine learning for entity recognition based on chunk annotation. The tools produced would facilitate reliable information extraction from primary care patient records, needed for the development of clinically-related research. The three medical concept types targeted in this thesis could contribute to epidemiological studies by enhancing the detection of co-morbidities, and better analysing the descriptions of patient experiences and treatments. The main contributions of the research reported in this thesis are: guidelines for chunk and concept annotation of clinical text, an approach to maximising agreement between human annotators, the Harvey Corpus, a method for using a standard part-of-speech tagging model in clinical text chunking, and a novel approach to recognising clinically relevant medical concepts.
43
Agaiby, Hany. "Word boundary detection for engineering applications." Thesis, University of the West of Scotland, 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.265933.
Full text
44
Hui, Colin Chiu Wing. "VLSI architectures for digital television applications." Thesis, Queen's University Belfast, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.387928.
Full text
45
Via, Cinzia Da. "Semiconductor pixel detectors for imaging applications." Thesis, University of Glasgow, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.362937.
Full text
46
Vomasta, Daniel. "Diarylethene derivatives and their applications : Salen derivatives in molecular recognition." kostenfrei, 2009. http://epub.uni-regensburg.de/13393/.
Full text
47
Castro, Ceron Ivan Francisco, and Badillo Andrea Graciela Garcia. "A Keyword Based Interactive Speech Recognition System for Embedded Applications." Thesis, Mälardalens högskola, Akademin för innovation, design och teknik, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-12479.
Full textAbstract:
Speech recognition has been an important area of research during the past decades. The usage of automatic speech recognition systems is rapidly increasing among different areas, such as mobile telephony, automotive, healthcare, robotics and more. However, despite the existence of many speech recognition systems, most of them use platform specific and non-publicly available software. Nevertheless, it is possible to develop speech recognition systems using already existing open source technology. The aim of this master's thesis is to develop an interactive and speaker independent speech recognition system. The system shall be able to identify predetermined keywords from incoming live speech and in response, play audio files with related information. Moreover, the system shall be able to provide a response even if no keyword was identified. For this project, the system was implemented using PocketSphinx, a speech recognition library, part of the open source Sphinx technology by the Carnegie Mellon University. During the implementation of this project, the automation of different steps of the process, was a key factor for a successful completion. This automation consisted on the development of different tools for the creation of the language model and the dictionary, two important components of the system. Similarly, the audio files to be played after identifying a keyword, as well as the evaluation of the system's performance, were fully automated. The tests run show encouraging results and demonstrate that the system is a feasible solution that could be implemented and tested in a real embedded application. Despite the good results, possible improvements can be implemented, such as the creation of a different phonetic dictionary to support different languages.
48
Huang, X. (Xiaohua). "Methods for facial expression recognition with applications in challenging situations." Doctoral thesis, Oulun yliopisto, 2014. http://urn.fi/urn:isbn:9789526206561.
Full textAbstract:
Abstract In recent years, facial expression recognition has become a useful scheme for computers to affectively understand the emotional state of human beings. Facial representation and facial expression recognition under unconstrained environments have been two critical issues for facial expression recognition systems. This thesis contributes to the research and development of facial expression recognition systems from two aspects: first, feature extraction for facial expression recognition, and second, applications to challenging conditions. Spatial and temporal feature extraction methods are introduced to provide effective and discriminative features for facial expression recognition. The thesis begins with a spatial feature extraction method. This descriptor exploits magnitude while it improves local quantized pattern using improved vector quantization. It also makes the statistical patterns domain-adaptive and compact. Then, the thesis discusses two spatiotemporal feature extraction methods. The first method uses monogenic signal analysis as a preprocessing stage and extracts spatiotemporal features using local binary pattern. The second method extracts sparse spatiotemporal features using sparse cuboids and spatiotemporal local binary pattern. Both methods increase the discriminative capability of local binary pattern in the temporal domain. Based on feature extraction methods, three practical conditions, including illumination variations, facial occlusion and pose changes, are studied for the applications of facial expression recognition. First, with near-infrared imaging technique, a discriminative component-based single feature descriptor is proposed to achieve a high degree of robustness and stability to illumination variations. Second, occlusion detection is proposed to dynamically detect the occluded face regions. A novel system is further designed for handling effectively facial occlusion. Lastly, multi-view discriminative neighbor preserving embedding is developed to deal with pose change, which formulates multi-view facial expression recognition as a generalized eigenvalue problem. Experimental results on publicly available databases show that the effectiveness of the proposed approaches for the applications of facial expression recognitionTiivistelmä Kasvonilmeiden tunnistamisesta on viime vuosina tullut tietokoneille hyödyllinen tapa ymmärtää affektiivisesti ihmisen tunnetilaa. Kasvojen esittäminen ja kasvonilmeiden tunnistaminen rajoittamattomissa ympäristöissä ovat olleet kaksi kriittistä ongelmaa kasvonilmeitä tunnistavien järjestelmien kannalta. Tämä väitöskirjatutkimus myötävaikuttaa kasvonilmeitä tunnistavien järjestelmien tutkimukseen ja kehittymiseen kahdesta näkökulmasta: piirteiden irrottamisesta kasvonilmeiden tunnistamista varten ja kasvonilmeiden tunnistamisesta haastavissa olosuhteissa. Työssä esitellään spatiaalisia ja temporaalisia piirteenirrotusmenetelmiä, jotka tuottavat tehokkaita ja erottelukykyisiä piirteitä kasvonilmeiden tunnistamiseen. Ensimmäisenä työssä esitellään spatiaalinen piirteenirrotusmenetelmä, joka parantaa paikallisia kvantisoituja piirteitä käyttämällä parannettua vektorikvantisointia. Menetelmä tekee myös tilastollisista malleista monikäyttöisiä ja tiiviitä. Seuraavaksi työssä esitellään kaksi spatiotemporaalista piirteenirrotusmenetelmää. Ensimmäinen näistä käyttää esikäsittelynä monogeenistä signaalianalyysiä ja irrottaa spatiotemporaaliset piirteet paikallisia binäärikuvioita käyttäen. Toinen menetelmä irrottaa harvoja spatiotemporaalisia piirteitä käyttäen harvoja kuusitahokkaita ja spatiotemporaalisia paikallisia binäärikuvioita. Molemmat menetelmät parantavat paikallisten binärikuvioiden erottelukykyä ajallisessa ulottuvuudessa. Piirteenirrotusmenetelmien pohjalta työssä tutkitaan kasvonilmeiden tunnistusta kolmessa käytännön olosuhteessa, joissa esiintyy vaihtelua valaistuksessa, okkluusiossa ja pään asennossa. Ensiksi ehdotetaan lähi-infrapuna kuvantamista hyödyntävää diskriminatiivistä komponenttipohjaista yhden piirteen kuvausta, jolla saavutetaan korkea suoritusvarmuus valaistuksen vaihtelun suhteen. Toiseksi ehdotetaan menetelmä okkluusion havainnointiin, jolla dynaamisesti havaitaan peittyneet kasvon alueet. Uudenlainen menetelmä on kehitetty käsittelemään kasvojen okkluusio tehokkaasti. Viimeiseksi työssä on kehitetty moninäkymäinen diskriminatiivisen naapuruston säilyttävään upottamiseen pohjautuva menetelmä käsittelemään pään asennon vaihtelut. Menetelmä kuvaa moninäkymäisen kasvonilmeiden tunnistamisen yleistettynä ominaisarvohajotelmana. Kokeelliset tulokset julkisilla tietokannoilla osoittavat tässä työssä ehdotetut menetelmät suorituskykyisiksi kasvonilmeiden tunnistamisessa
49
Chen, Guangyi. "Applications of wavelet transforms in pattern recognition and de-noising." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape7/PQDD_0006/MQ43552.pdf.
Full text
50
Raghavan, Sridhar. "APPLICATIONS OF LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION TO FATIGUE DETECTION." MSSTATE, 2006. http://sun.library.msstate.edu/ETD-db/theses/available/etd-06302006-094831/.
Full textAbstract:
Applications of speech recognition have evolved in recent years from simple transcription tasks to metadata analysis. This thesis explores the use of speech recognition for automated fatigue detection. The fatigue detection system relies on accurate phonetic alignments from a speech recognition system. The main challenge addressed in this thesis was to make the process of phonetic alignment using speech recognition robust to out of vocabulary words. This requirement was achieved by incorporating confidence measures, which significantly reduce false positives in speech recognition output. This allowed the performance of the fatigue detection system to match the results of other cognitive tests based on the Sleep Onset Latency (SOL) and Sleep, Activity, Fatigue, and Task Effectiveness (SAFTE). Confidence measures reduced the squared error between voice-based fatigue prediction and SAFTE by 20% when 67.1% of the words in the test set were out of vocabulary words.