Dissertations / Theses on the topic 'Feature Recognition Methods'
To see the other types of publications on this topic, follow the link: Feature Recognition Methods.
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 'Feature Recognition Methods.'
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
Wu, Zhili. "Kernel based learning methods for pattern and feature analysis." HKBU Institutional Repository, 2004. http://repository.hkbu.edu.hk/etd_ra/619.
Full text
2
Cohen, Gregory Kevin. "Event-Based Feature Detection, Recognition and Classification." Thesis, Paris 6, 2016. http://www.theses.fr/2016PA066204/document.
Full textAbstract:
La detection, le suivi de cible et la reconnaissance de primitives visuelles constituent des problèmes fondamentaux de la vision robotique. Ces problématiques sont réputés difficiles et sources de défis. Malgré les progrès en puissance de calcul des machines, le gain en résolution et en fréquence des capteurs, l’état-de-l’art de la vision robotique peine à atteindre des performances en coût d’énergie et en robustesse qu’offre la vision biologique. L’apparition des nouveaux capteurs, appelés "rétines de silicium” tel que le DVS (Dynamic Vision Sensor) et l’ATIS (Asynchronous Time-based Imaging Sensor) reproduisant certaines fonctionnalités des rétines biologiques, ouvre la voie à de nouveaux paradigmes pour décrire et modéliser la perception visuelle, ainsi que pour traiter l’information visuelle qui en résulte. Les tâches de suivi et de reconnaissance de formes requièrent toujours la caractérisation et la mise en correspondance de primitives visuelles. La détection de ces dernières et leur description nécessitent des approches fondamentalement différentes de celles employées en vision robotique traditionnelle. Cette thèse développe et formalise de nouvelles méthodes de détection et de caractérisation de primitives spatio-temporel des signaux acquis par les rétines de silicium (plus communément appelés capteurs “event-based”). Une structure théorique pour les tâches de détection, de suivi, de reconnaissance et de classification de primitives est proposée. Elle est ensuite validée par des données issues de ces capteurs “event-based”,ainsi que par des bases données standard du domaine de la reconnaissance de formes, convertit au préalable à un format compatible avec la representation “événement”. Les résultats présentés dans cette thèse démontrent les potentiels et l’efficacité des systèmes "event-based”. Ce travail fournit une analyse approfondie de différentes méthodes de reconnaissance de forme et de classification “event-based". Cette thèse propose ensuite deux solutions basées sur les primitives. Deux mécanismes d’apprentissage, un purement événementiel et un autre, itératif, sont développés puis évalués pour leur capacité de classification et de robustesse. Les résultats démontrent la validité de la classification “event-based” et souligne l’importance de la dynamique de la scène dans les tâches primordiales de définitions des primitives et de leur détection et caractétisationOne of the fundamental tasks underlying much of computer vision is the detection, tracking and recognition of visual features. It is an inherently difficult and challenging problem, and despite the advances in computational power, pixel resolution, and frame rates, even the state-of-the-art methods fall far short of the robustness, reliability and energy consumption of biological vision systems. Silicon retinas, such as the Dynamic Vision Sensor (DVS) and Asynchronous Time-based Imaging Sensor (ATIS), attempt to replicate some of the benefits of biological retinas and provide a vastly different paradigm in which to sense and process the visual world. Tasks such as tracking and object recognition still require the identification and matching of local visual features, but the detection, extraction and recognition of features requires a fundamentally different approach, and the methods that are commonly applied to conventional imaging are not directly applicable. This thesis explores methods to detect features in the spatio-temporal information from event-based vision sensors. The nature of features in such data is explored, and methods to determine and detect features are demonstrated. A framework for detecting, tracking, recognising and classifying features is developed and validated using real-world data and event-based variations of existing computer vision datasets and benchmarks. The results presented in this thesis demonstrate the potential and efficacy of event-based systems. This work provides an in-depth analysis of different event-based methods for object recognition and classification and introduces two feature-based methods. Two learning systems, one event-based and the other iterative, were used to explore the nature and classification ability of these methods. The results demonstrate the viability of event-based classification and the importance and role of motion in event-based feature detection
3
Nelson, Jonas. "Methods for Locating Distinct Features in Fingerprint Images." Thesis, Linköping University, Department of Science and Technology, 2002. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-1147.
Full textAbstract:
With the advance of the modern information society, the importance of reliable identity authentication has increased dramatically. Using biometrics as a means for verifying the identity of a person increases both the security and the convenience of the systems. By using yourself to verify your identity such risks as lost keys and misplaced passwords are removed and by virtue of this, convenience is also increased. The most mature and well-developed biometric technique is fingerprint recognition. Fingerprints are unique for each individual and they do not change over time, which is very desirable in this application. There are multitudes of approaches to fingerprint recognition, most of which work by identifying so called minutiae and match fingerprints based on these.
In this diploma work, two alternative methods for locating distinct features in fingerprint images have been evaluated. The Template Correlation Method is based on the correlation between the image and templates created to approximate the homogenous ridge/valley areas in the fingerprint. The high-dimension of the feature vectors from correlation is reduced through principal component analysis. By visualising the dimension reduced data by ordinary plotting and observing the result classification is performed by locating anomalies in feature space, where distinct features are located away from the non-distinct.
The Circular Sampling Method works by sampling in concentric circles around selected points in the image and evaluating the frequency content of the resulting functions. Each images used here contains 30400 pixels which leads to sampling in many points that are of no interest. By selecting the sampling points this number can be reduced. Two approaches to sampling points selection has been evaluated. The first restricts sampling to occur only along valley bottoms of the image, whereas the second uses orientation histograms to select regions where there is no single dominant direction as sampling positions. For each sampling position an intensity function is achieved by circular sampling and a frequency spectrum of this function is achieved through the Fast Fourier Transform. Applying criteria to the relationships of the frequency components classifies each sampling location as either distinct or non-distinct.
Using a cyclic approach to evaluate the methods and their potential makes selection at various stages possible. Only the Circular Sampling Method survived the first cycle, and therefore all tests from that point on are performed on thismethod alone. Two main errors arise from the tests, where the most prominent being the number of spurious points located by the method. The second, which is equally serious but not as common, is when the method misclassifies visually distinct features as non-distinct. Regardless of the problems, these tests indicate that the method holds potential but that it needs to be subject to further testing and optimisation. These tests should focus on the three main properties of the method: noise sensitivity, radial dependency and translation sensitivity.
4
Hassan, Wael. "Comparing Geomorphometric Pattern Recognition Methods for Semi-Automated Landform Mapping." Ohio University / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou160690391009081.
Full text
5
Brennan, Michael. "Comparison of automated feature extraction methods for image based screening of cancer cells." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-167602.
Full textAbstract:
Image based screening is an important tool used in research for development of drugs to fight cancer. Phase contrast video microscopy - a cheap and fast image screening technology - enables a rapid generation of large amounts of data, which requires a fast method for analysis of this data. As videos contain a lot of redundant information, the difficulty is to extract usable information in form of features from the videos, by compressing available information, or filter out redundant data. In this thesis, the problem is approached in an experimental fashion where three different methods have been devised and tested, to evaluate different ways to automatically extract features from phase contrast microscopy videos containing cultured cancer cells. The three methods considered are, in order: an adaptive linear filter, an on-line clustering algorithm, and an artificial neural network. The ambition is that outputs from these methods can create time-varying histograms of features that can be used in further mathematical modeling of cell dynamics. It is concluded that, while the results of the first method is not impressive and can be dismissed, the remaining two are more promising and are able to successfully extract features automatically and aggregate them into time-varying histograms.
6
Le, Faucheur Xavier Jean Maurice. "Statistical methods for feature extraction in shape analysis and bioinformatics." Diss., Georgia Institute of Technology, 2010. http://hdl.handle.net/1853/33911.
Full textAbstract:
The presented research explores two different problems of statistical data analysis.
In the first part of this thesis, a method for 3D shape representation, compression and smoothing is presented. First, a technique for encoding non-spherical surfaces using second generation wavelet decomposition is described. Second, a novel model is proposed for wavelet-based surface enhancement. This part of the work aims to develop an efficient algorithm for removing irrelevant and noise-like variations from 3D shapes. Surfaces are encoded using second generation wavelets, and the proposed methodology consists of separating noise-like wavelet coefficients from those contributing to the relevant part of the signal. The empirical-based Bayesian models developed in this thesis threshold wavelet coefficients in an adaptive and robust manner. Once thresholding is performed, irrelevant coefficients are removed and the inverse wavelet transform is applied to the clean set of wavelet coefficients. Experimental results show the efficiency of the proposed technique for surface smoothing and compression.
The second part of this thesis proposes using a non-parametric clustering method for studying RNA (RiboNucleic Acid) conformations. The local conformation of RNA molecules is an important factor in determining their catalytic and binding properties. RNA conformations can be characterized by a finite set of parameters that define the local arrangement of the molecule in space. Their analysis is particularly difficult due to the large number of degrees of freedom, such as torsion angles and inter-atomic distances among interacting residues. In order to understand and analyze the structural variability of RNA molecules, this work proposes a methodology for detecting repetitive conformational sub-structures along RNA strands. Clusters of similar structures in the conformational space are obtained using a nearest-neighbor search method based on the statistical mechanical Potts model. The proposed technique is a mostly automatic clustering algorithm and may be applied to problems where there is no prior knowledge on the structure of the data space, in contrast to many other clustering techniques. First, results are reported for both single residue conformations- where the parameter set of the data space includes four to seven torsional angles-, and base pair geometries. For both types of data sets, a very good match is observed between the results of the proposed clustering method and other known classifications, with only few exceptions. Second, new results are reported for base stacking geometries. In this case, the proposed classification is validated with respect to specific geometrical constraints, while the content and geometry of the new clusters are fully analyzed.
7
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
8
Oliveira, e. Cruz Rafael Menelau. "Methods for dynamic selection and fusion of ensemble of classifiers." Universidade Federal de Pernambuco, 2011. https://repositorio.ufpe.br/handle/123456789/2436.
Full textAbstract:
Made available in DSpace on 2014-06-12T15:58:13Z (GMT). No. of bitstreams: 2
arquivo3310_1.pdf: 8155353 bytes, checksum: 2f4dcd5adb2b0b1a23c40bf343b36b34 (MD5)
license.txt: 1748 bytes, checksum: 8a4605be74aa9ea9d79846c1fba20a33 (MD5)
Previous issue date: 2011Faculdade de Amparo à Ciência e Tecnologia do Estado de Pernambuco
Ensemble of Classifiers (EoC) é uma nova alternative para alcançar altas taxas de reconhecimento em sistemas de reconhecimento de padrões. O uso de ensemble é motivado pelo fato de que classificadores diferentes conseguem reconhecer padrões diferentes, portanto, eles são complementares. Neste trabalho, as metodologias de EoC são exploradas com o intuito de melhorar a taxa de reconhecimento em diferentes problemas. Primeiramente o problema do reconhecimento de caracteres é abordado. Este trabalho propõe uma nova metodologia que utiliza múltiplas técnicas de extração de características, cada uma utilizando uma abordagem diferente (bordas, gradiente, projeções). Cada técnica é vista como um sub-problema possuindo seu próprio classificador. As saídas deste classificador são utilizadas como entrada para um novo classificador que é treinado para fazer a combinação (fusão) dos resultados. Experimentos realizados demonstram que a proposta apresentou o melhor resultado na literatura pra problemas tanto de reconhecimento de dígitos como para o reconhecimento de letras. A segunda parte da dissertação trata da seleção dinâmica de classificadores (DCS). Esta estratégia é motivada pelo fato que nem todo classificador pertencente ao ensemble é um especialista para todo padrão de teste. A seleção dinâmica tenta selecionar apenas os classificadores que possuem melhor desempenho em uma dada região próxima ao padrão de entrada para classificar o padrão de entrada. É feito um estudo sobre o comportamento das técnicas de DCS demonstrando que elas são limitadas pela qualidade da região em volta do padrão de entrada. Baseada nesta análise, duas técnicas para seleção dinâmica de classificadores são propostas. A primeira utiliza filtros para redução de ruídos próximos do padrão de testes. A segunda é uma nova proposta que visa extrair diferentes tipos de informação, a partir do comportamento dos classificadores, e utiliza estas informações para decidir se um classificador deve ser selecionado ou não. Experimentos conduzidos em diversos problemas de reconhecimento de padrões demonstram que as técnicas propostas apresentam um aumento de performance significante
9
Křístek, Jakub. "Rozpoznávání ručně kreslených objektů." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2015. http://www.nusl.cz/ntk/nusl-221329.
Full textAbstract:
This work deals with recognition of hand-drawn objects traced by children with mental disorders. The aim is to classify object’s geometrical primitives into classes so then can be plotted along with the idealized shape of the input object. Level of mental retardation is determined by the variance of the input (drawn) object from idealized shape of the object (artwork).
10
Radermacher, Matthew Jeffery. "Pattern Recognition and Feature Extraction Using Liar-Derived Elevation Models in GIS: A Comparison Between Visualization Techniques and Automated Methods for Identifying Prehistoric Ditch-Fortified Sites in North Dakota." Thesis, North Dakota State University, 2016. https://hdl.handle.net/10365/28010.
Full textAbstract:
As technologies advance in the fields of geology and computer science, new methods in remote sensing, including data acquisition and analyses, make it possible to accurately model diverse landscapes. Archaeological applications of these systems are becoming increasingly popular, especially in regards to site prospection and the geospatial analysis of cultural features. Different methodologies were used to identify fortified ditch features of anthropogenic origin using aerial lidar from known prehistoric sites in North Dakota. The results were compared in an attempt to develop a system aimed at detecting similar, unrecorded morphological features on the landscape. The successful development of this program will allow archaeological investigators to review topography and locate specific features on the surface that otherwise could be difficult to identify as a result of poor visibility in the field.ND NASA EPSCoR
North Dakota State University
11
Parkhi, Omkar Moreshwar. "Features and methods for improving large scale face recognition." Thesis, University of Oxford, 2015. https://ora.ox.ac.uk/objects/uuid:7704244a-b327-4e5c-a58e-7bfe769ed988.
Full textAbstract:
This thesis investigates vector representations for face recognition, and uses these representations for a number of tasks in image and video datasets. First, we look at different representations for faces in images and videos. The objective is to learn compact yet effective representations for describing faces. We first investigate the use of "Fisher Vector" descriptors for this task. We show that these descriptors are perfectly suited for face representation tasks. We also investigate various approaches to effectively reduce their dimension while improving their performance further. These "Fisher Vector" features are also amenable to extreme compression and work equally well when compressed by over 2000 times as compared to their non compressed counterparts. These features achieved the state-of-the-art results on challenging public benchmarks until the re-introduction of Convolution Neural Networks (CNNs) in the community. Second, we investigate the use of "Very Deep" architectures for face representation tasks. For training these networks, we collected one of the largest annotated public datasets of celebrity faces with minimum manual intervention. We bring out specific details of these network architectures and their training objective functions essential to their performance and achieve state-of-art result on challenging datasets. Having developed these representation, we propose a method for labeling faces in the challenging environment of broadcast videos using their associated textual data, such as subtitles and transcripts. We show that our CNN representation is well suited for this task. We also propose a scheme to automatically differentiate the primary cast of a TV serial or movie from that of the background characters. We modify existing methods of collecting supervision from textual data and show that the careful alignment of video and textual data results in significant improvement in the amount of training data collected automatically, which has a direct positive impact on the performance of labeling mechanisms. We provide extensive evaluations on different benchmark datasets achieving, again, state-of-the-art results. Further we show that both the shallow as well the deep methods have excellent capabilities in switching modalities from photos to paintings and vice-a-versa. We propose a system to retrieve paintings for similar looking people given a picture and investigate the use of facial attributes for this task. Finally, we show that an on-the-fly real time search system can be built to search through thousands of hours of video data starting from a text query. We propose product quantization schemes for making face representations memory efficient. We also present the demo system based on this design for the British Broadcasting Corporation (BBC) to search through their archive. All of these contributions have been designed with a keen eye on their application in the real world. As a result, most of chapters have an associated code release and a working online demonstration.
12
Tvoroshenko, I. S., and Ya Bielinskyi. "On the features of methods of processing and recognition of handwritten text." Thesis, Boston, USA, 2021. https://openarchive.nure.ua/handle/document/17612.
Full text
13
Chan, Oscar. "Prosodic features for a maximum entropy language model." University of Western Australia. School of Electrical, Electronic and Computer Engineering, 2008. http://theses.library.uwa.edu.au/adt-WU2008.0244.
Full textAbstract:
A statistical language model attempts to characterise the patterns present in a natural language as a probability distribution defined over word sequences. Typically, they are trained using word co-occurrence statistics from a large sample of text. In some language modelling applications, such as automatic speech recognition (ASR), the availability of acoustic data provides an additional source of knowledge. This contains, amongst other things, the melodic and rhythmic aspects of speech referred to as prosody. Although prosody has been found to be an important factor in human speech recognition, its use in ASR has been limited. The goal of this research is to investigate how prosodic information can be employed to improve the language modelling component of a continuous speech recognition system. Because prosodic features are largely suprasegmental, operating over units larger than the phonetic segment, the language model is an appropriate place to incorporate such information. The prosodic features and standard language model features are combined under the maximum entropy framework, which provides an elegant solution to modelling information obtained from multiple, differing knowledge sources. We derive features for the model based on perceptually transcribed Tones and Break Indices (ToBI) labels, and analyse their contribution to the word recognition task. While ToBI has a solid foundation in linguistic theory, the need for human transcribers conflicts with the statistical model's requirement for a large quantity of training data. We therefore also examine the applicability of features which can be automatically extracted from the speech signal. We develop representations of an utterance's prosodic context using fundamental frequency, energy and duration features, which can be directly incorporated into the model without the need for manual labelling. Dimensionality reduction techniques are also explored with the aim of reducing the computational costs associated with training a maximum entropy model. Experiments on a prosodically transcribed corpus show that small but statistically significant reductions to perplexity and word error rates can be obtained by using both manually transcribed and automatically extracted features.
14
Smith, R. S. "Angular feature extraction and ensemble classification method for 2D, 2.5D and 3D face recognition." Thesis, University of Surrey, 2008. http://epubs.surrey.ac.uk/843069/.
Full textAbstract:
It has been recognised that, within the context of face recognition, angular separation between centred feature vectors is a useful measure of dissimilarity. In this thesis we explore this observation in more detail and compare and contrast angular separation with the Euclidean, Manhattan and Mahalonobis distance metrics. This is applied to 2D, 2.5D and 3D face images and the investigation is done in conjunction with various feature extraction techniques such as local binary patterns (LBP) and linear discriminant analysis (LDA). We also employ error-correcting output code (ECOC) ensembles of support vector machines (SVMs) to project feature vectors non-linearly into a new and more discriminative feature space. It is shown that, for both face verification and face recognition tasks, angular separation is a more discerning dissimilarity measure than the others. It is also shown that the effect of applying the feature extraction algorithms described above is to considerably sharpen and enhance the ability of all metrics, but in particular angular separation, to distinguish inter-personal from extra-personal face image differences. A novel technique, known as angularisation, is introduced by which a data set that is well separated in the angular sense can be mapped into a new feature space in which other metrics are equally discriminative. This operation can be performed separately or it can be incorporated into an SVM kernel. The benefit of angularisation is that it allows strong classification methods to take advantage of angular separation without explicitly incorporating it into their construction. It is shown that the accuracy of ECOC ensembles can be improved in this way. A further aspect of the research is to compare the effectiveness of the ECOC approach to constructing ensembles of SVM base classifiers with that of binary hierarchical classifiers (BHC). Experiments are performed which lead to the conclusion that, for face recognition problems, ECOC yields greater classification accuracy than the BHC method. This is attributed primarily to the fact that the size of the training set decreases along a path from the root node to a leaf node of the BHC tree and this leads to great difficulties in constructing accurate base classifiers at the lower nodes.
15
Stoyanova, Radka. "Development and application of methods for enhancing features in NMR spectra for pattern recognition." Thesis, Imperial College London, 2005. http://hdl.handle.net/10044/1/8269.
Full text
16
Zacherl, Walter David. "Method for Registering Lidar Data in Restrictive, Tunnel-Like Environments." Diss., The University of Arizona, 2016. http://hdl.handle.net/10150/613145.
Full textAbstract:
A new method of registering multiple range datasets collected in a GPS-denied, tunnel-like environment is presented. The method is designed to function with minimal user inputs and be effective over a wide range of changes in observation angle. The method is initially developed to operate on data in a general 2.5D coordinate system. Then, the general registration method is specifically tailored to a 2.5D spherical coordinate system. To apply the method, the range data is first filtered with a series of discrete Gaussian-based filters to construct a second-order Taylor series approximation to the surface about each sampled point. Finally, principal curvatures are calculated and compared across neighboring datasets to determine homologies and the best fit transfer matrix. The new method relaxes the minimum change in perspective requirement between neighboring datasets typical of other algorithms. Results from the application of the method on both synthetic and real-world data are shown. The real-world data comes from a series of high explosive tests performed in a tunnel environment. The tunnels were oriented horizontally in rock and constructed with boring equipment. The tunnel surfaces were surveyed with a Faro Focus3D terrestrial panorama scanning light detection and ranging (lidar) system both before and after a high explosive device was detonated inside the tunnel with the intent of documenting damage to the tunnel surface.
17
Ding, Sheng. "A Detachable LSTM with Residual-Autoencoder Features Method for Motion Recognition in Video Sequences." The Ohio State University, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=osu160673417735023.
Full text
18
Pavani, Sri-Kaushik. "Methods for face detection and adaptive face recognition." Doctoral thesis, Universitat Pompeu Fabra, 2010. http://hdl.handle.net/10803/7567.
Full textAbstract:
The focus of this thesis is on facial biometrics; specifically in the problems of face detection and face recognition. Despite intensive research over the last 20 years, the technology is not foolproof, which is why we do not see use of face recognition systems in critical sectors such as banking. In this thesis, we focus on three sub-problems in these two areas of research. Firstly, we propose methods to improve the speed-accuracy trade-off of the state-of-the-art face detector. Secondly, we consider a problem that is often ignored in the literature: to decrease the training time of the detectors. We propose two techniques to this end. Thirdly, we present a detailed large-scale study on self-updating face recognition systems in an attempt to answer if continuously changing facial appearance can be learnt automatically.L'objectiu d'aquesta tesi és sobre biometria facial, específicament en els problemes de detecció de rostres i reconeixement facial. Malgrat la intensa recerca durant els últims 20 anys, la tecnologia no és infalible, de manera que no veiem l'ús dels sistemes de reconeixement de rostres en sectors crítics com la banca. En aquesta tesi, ens centrem en tres sub-problemes en aquestes dues àrees de recerca. En primer lloc, es proposa mètodes per millorar l'equilibri entre la precisió i la velocitat del detector de cares d'última generació. En segon lloc, considerem un problema que sovint s'ignora en la literatura: disminuir el temps de formació dels detectors. Es proposen dues tècniques per a aquest fi. En tercer lloc, es presenta un estudi detallat a gran escala sobre l'auto-actualització dels sistemes de reconeixement facial en un intent de respondre si el canvi constant de l'aparença facial es pot aprendre de forma automàtica.
19
Mushtaq, Aleem. "An integrated approach to feature compensation combining particle filters and Hidden Markov Models for robust speech recognition." Diss., Georgia Institute of Technology, 2013. http://hdl.handle.net/1853/48982.
Full textAbstract:
The performance of automatic speech recognition systems often degrades in adverse conditions where there is a mismatch between training and testing conditions. This is true for most modern systems which employ Hidden Markov Models (HMMs) to decode speech utterances. One strategy is to map the distorted features back to clean speech features that correspond well to the features used for training of HMMs. This can be achieved by treating the noisy speech as the distorted version of the clean speech of interest. Under this framework, we can track and consequently extract the underlying clean speech from the noisy signal and use this derived signal to perform utterance recognition. Particle filter is a versatile tracking technique that can be used where often conventional techniques such as Kalman filter fall short. We propose a particle filters based algorithm to compensate the corrupted features according to an additive noise model incorporating both the statistics from clean speech HMMs and observed background noise to map noisy features back to clean speech features. Instead of using specific knowledge at the model and state levels from HMMs which is hard to estimate, we pool model states into clusters as side information. Since each cluster encompasses more statistics when compared to the original HMM states, there is a higher possibility that the newly formed probability density function at the cluster level can cover the underlying speech variation to generate appropriate particle filter samples for feature compensation. Additionally, a dynamic joint tracking framework to monitor the clean speech signal and noise simultaneously is also introduced to obtain good noise statistics. In this approach, the information available from clean speech tracking can be effectively used for noise estimation. The availability of dynamic noise information can enhance the robustness of the algorithm in case of large fluctuations in noise parameters within an utterance. Testing the proposed PF-based compensation scheme on the Aurora 2 connected digit recognition task, we achieve an error reduction of 12.15% from the best multi-condition trained models using this integrated PF-HMM framework to estimate the cluster-based HMM state sequence information. Finally, we extended the PFC framework and evaluated it on a large-vocabulary recognition task, and showed that PFC works well for large-vocabulary systems also.
20
Secmen, Mustafa. "A Novel Music Algorithm Based Electromagnetic Target Recognition Method In Resonance Region For The Classification Of Single And Multiple Targets." Phd thesis, METU, 2008. http://etd.lib.metu.edu.tr/upload/2/12609306/index.pdf.
Full textAbstract:
This thesis presents a novel aspect and polarization invariant electromagnetic target recognition technique in resonance region based on use of MUSIC algorithm for the extraction of natural-resonance related target features. In the suggested method, the feature patterns called &ldquoMUSIC Spectrum Matrices (MSMs)&rdquo
are constructed for each candidate target at each reference aspect angle using targets&rsquo
scattered data at different late-time intervals. These individual MSMs correspond to maps of targets&rsquo
natural-resonance related power distributions. All these patterns are first used to obtain optimal late-time interval for classifier design and a &ldquo
Fused MUSIC Spectrum Matrix (FMSM)&rdquo
is generated over this interval for each target by superposing MSMs. The resulting FMSMs include more complete information for target resonances and are almost insensitive to aspect and polarization. In case of multiple target recognition, the relative locations of a multi-target group and separation distance between targets are also important factors. Therefore, MSM features are computed for each multi-target group at each &ldquo
reference aspect/topology&rdquo
combination to determine the optimum late-time interval. The FMSM feature of a given multi-target group is obtained by the superposition of all these aspect and topology dependent MSMs. In both single and multiple target recognition cases, the resulting FMSM power patterns are main target features of the designed classifier to be used during real-time decisions. At decision phase, the unknown test target is classified either as one of the candidate targets or as an alien target by comparing correlation coefficients computed between MSM of test signal and FMSM of each candidate target.
21
Gutiérrez, Rubert Santiago Carlos. "Análisis y procesado tecnológico del modelo sólido de una pieza para determinar sus elementos característicos de mecanizado." Doctoral thesis, Universitat Politècnica de València, 2008. http://hdl.handle.net/10251/1963.
Full textAbstract:
Una de las primeras etapas en la Planificación de Procesos asistida por ordenador, para procesos de mecanizado por arranque de material, consiste en identificar las zonas de material a eliminar en el bruto de partida para generar la pieza. El resultado es un conjunto de entidades llamadas: Elementos Característicos de Mecanizado, que tienen una clara relación con las operaciones de mecanizado.
Al procedimiento de obtención automática de estas entidades se le denomina: reconocimiento automático de Elementos Característicos de Mecanizado (AFR, Automatic Feature Recognition), en el que partiendo del modelo 3D del bruto y de la pieza se establecen las entidades de trabajo adecuadas (Elementos Característicos de Mecanizado). Estas entidades contienen la información necesaria para poder llevar a cabo una Planificación de Procesos automática. A su vez, la información se va completando y ampliando a medida que se avanza en las etapas de la Planificación.
En la Tesis se plantea el reconocimiento automático de Elementos Característicos de Mecanizado como una de las primeras etapas de la Planificación de Procesos, y que permite el enlace con el diseño asistido por ordenador. Este reconocimiento debe tener un planteamiento dinámico, ofreciendo distintas opciones. Su solución no debe ser una entrada estática, prefijada, para el resto de etapas de la Planificación. El proceso de reconocimiento está fuertemente influenciado por conceptos y decisiones de índole tecnológico (tipos de herramientas, movimientos característicos de los procesos, influencia del corte vinculado, ), que lo guían y que permiten obtener resultados válidos en la aplicación destino: el mecanizado.
Atendiendo a este planteamiento, la Tesis ofrece una solución general y completa al proceso de reconocimiento automático de Elementos Característicos de Mecanizado, teniendo en cuenta a los llamados procesos convencionales (torneado, fresado, limado, rectificado, etc.). La solución propuesta no se restringe a piezasGutiérrez Rubert, SC. (2007). Análisis y procesado tecnológico del modelo sólido de una pieza para determinar sus elementos característicos de mecanizado [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/1963
Palancia
22
Ben, Soltana Wael. "Optimisation de stratégies de fusion pour la reconnaissance de visages 3D." Phd thesis, Ecole Centrale de Lyon, 2012. http://tel.archives-ouvertes.fr/tel-01070638.
Full textAbstract:
La reconnaissance faciale (RF) est un domaine de recherche très actif en raison de ses nombreuses applications dans le domaine de la vision par ordinateur en général et en biométrie en particulier. Cet intérêt est motivé par plusieurs raisons. D'abord, le visage est universel. Ensuite, il est le moyen le plus naturel par les êtres humains de s'identifier les uns des autres. Enfin, le visage en tant que modalité biométrique est présente un caractère non intrusif, ce qui le distingue d'autres modalités biométriques comme l'iris ou l'emprunte digitale. La RF représente aussi des défis scientifiques importants. D'abord parce que tous les visages humains ont des configurations similaires. Ensuite, avec les images faciales 2D que l'on peut acquérir facilement, la variation intra-classe, due à des facteurs comme le changement de poses et de conditions d'éclairage, les variations d'expressions faciales, le vieillissement, est bien plus importante que la variation inter-classe.Avec l'arrivée des systèmes d'acquisition 3D capables de capturer la profondeur d'objets, la reconnaissance faciale 3D (RF 3D) a émergé comme une voie prometteuse pour traiter les deux problèmes non résolus en 2D, à savoir les variations de pose et d'éclairage. En effet, les caméras 3D délivrent généralement les scans 3D de visages avec leurs images de texture alignées. Une solution en RF 3D peut donc tirer parti d'une fusion avisée d'informations de forme en 3D et celles de texture en 2D. En effet, étant donné que les scans 3D de visage offrent à la fois les surfaces faciales pour la modalité 3D pure et les images de texture 2D alignées, le nombre de possibilités de fusion pour optimiser le taux de reconnaissance est donc considérable. L'optimisation de stratégies de fusion pour une meilleure RF 3D est l'objectif principal de nos travaux de recherche menés dans cette thèse.Dans l'état d'art, diverses stratégies de fusion ont été proposées pour la reconnaissance de visages 3D, allant de la fusion précoce "early fusion" opérant au niveau de caractéristiques à la fusion tardive "late fusion" sur les sorties de classifieurs, en passant par de nombreuses stratégies intermédiaires. Pour les stratégies de fusion tardive, nous distinguons encore des combinaisons en parallèle, en cascade ou multi-niveaux. Une exploration exhaustive d'un tel espace étant impossible, il faut donc recourir à des solutions heuristiques qui constituent nos démarches de base dans le cadre des travaux de cette thèse.En plus, en s'inscrivant dans un cadre de systèmes biométriques, les critères d'optimalité des stratégies de fusion restent des questions primordiales. En effet, une stratégie de fusion est dite optimisée si elle est capable d'intégrer et de tirer parti des différentes modalités et, plus largement, des différentes informations extraites lors du processus de reconnaissance quelque soit leur niveau d'abstraction et, par conséquent, de difficulté.Pour surmonter toutes ces difficultés et proposer une solution optimisée, notre démarche s'appuie d'une part sur l'apprentissage qui permet de qualifier sur des données d'entrainement les experts 2D ou 3D, selon des critères de performance comme ERR, et d'autre part l'utilisation de stratégie d'optimisation heuristique comme le recuit simulé qui permet d'optimiser les mélanges des experts à fusionner. [...]
23
Lin, Meng-kai, and 林盟凱. "Feature Exponent Adjustment Methods in Robust Speech Recognition." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/51556065034316819061.
Full textAbstract:
碩士國立暨南國際大學
電機工程學系
94
The performance of a speech recognition system is often degraded due to the mismatch between the environments of development and application. One of the major sources that give rise to this mismatch is, additive noise. The approaches for handling the problem of additive noise can be divided into three classes, speech enhancement, robust representation of speech, and compensation of speech models. In this thesis, the discussed methods belong to the first class, speech enhancement techniques. A common characteristic of our studied and proposed approaches in this thesis is the processing of exponentiation. When the exponentiation is performed on the original mel-frequency cepstral coefficients (MFCC), the resulted method is called cepstral exponent adjustment (CEA). On the other hand, when the exponentiation is carried out on the logarithmic spectrum or directly replace the logarithm operation, during the derivation process of MFCC, the resulted algorithms are called Exponentiated log-MelFBS (ExpoMFCC) and root Mel-filter bank spectrum (RMFCC), respectively. As a result, the three and applied to obtain new speech features for recognition in a noisy environment. Experimental results show that they apparently enhance the robustness of the speech features and thus improve the recognition accuracy. Moreover, they can be integrated with other robustness to obtain further improvement.
24
Zheng, Zhi-Kuan, and 鄭智寬. "A Study of Feature Extraction Methods for Continuous Speech Recognition." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/28588053629966750927.
Full textAbstract:
碩士大葉大學
電信工程學系碩士班
93
The performance of a speech recognition system is directly affected by the speech feature extraction stage. In this study, we compare the performance of speech recognition system using various kinds of static speech features including the linear predictive coding coefficients, the LPC reflection coefficients, the LPC cepstral coefficients, and the Mel-Frequency cepstral coefficients. We propose a dynamic speech feature extraction method that uses Hamming window weighted distortion measure to fit a feature vector sequence to the best matched parameterized dynamic trajectory. The performance of the proposed dynamic speech feature extraction method is compared to that of the traditional dynamic feature extraction method using rectangular window weighted distortion measure. In this thesis, Mel-Frequency cepstral coefficients outperform other features for speech recognition. Experimental results also show that the proposed dynamic speech feature extraction method using Hamming window weighted distortion measure do better than that using rectangle window weighted distortion measure. The window length used to estimate the dynamic feature is varied to see its effect on the recognition performance. We find that the system performance is less sensitive to the length of Hamming window. As we make various combinations of static and dynamic speech features, we find that the best performance is achieved by combing the static feature, the first order dynamic feature, and the second order dynamic feature. For noisy speech recognition, we use the spectral subtraction method to compensate for the noise effect. We find that the proposed Hamming window weighted dynamic speech feature extraction method can also improve the system performance under noisy environments. We also find that, under noisy environments, both of the length of the speech frame used to calculate the static feature and the length of the window used to calculate the dynamic feature should adequately increase to get better performance.
25
"Statistical approaches for facial feature extraction and face recognition." 2004. http://library.cuhk.edu.hk/record=b5892170.
Full textAbstract:
Sin Ka Yu = 抽取臉孔特徵及辨認臉孔的統計學方法 / 冼家裕.Thesis (M.Phil.)--Chinese University of Hong Kong, 2004.
Includes bibliographical references (leaves 86-90).
Text in English; abstracts in English and Chinese.
Sin Ka Yu = Chou qu lian kong te zheng ji bian ren lian kong de tong ji xue fang fa / Xian Jiayu.
Chapter Chapter 1. --- Introduction --- p.1
Chapter 1.1. --- Motivation --- p.1
Chapter 1.2. --- Objectives --- p.4
Chapter 1.3. --- Organization of the thesis --- p.4
Chapter Chapter 2. --- Facial Feature Extraction --- p.6
Chapter 2.1. --- Introduction --- p.6
Chapter 2.2. --- Reviews of Statistical Approach --- p.8
Chapter 2.2.1. --- Eigenfaces --- p.8
Chapter 2.2.1.1. --- Eigenfeatures Error! Bookmark not defined
Chapter 2.2.3. --- Singular Value Decomposition --- p.14
Chapter 2.2.4. --- Summary --- p.15
Chapter 2.3. --- Review of fiducial point localization methods --- p.16
Chapter 2.3.1. --- Symmetry based Approach --- p.16
Chapter 2.3.2. --- Color Based Approaches --- p.17
Chapter 2.3.3. --- Integral Projection --- p.17
Chapter 2.3.4. --- Deformable Template --- p.20
Chapter 2.4. --- Corner-based Fiducial Point Localization --- p.22
Chapter 2.4.1. --- Facial Region Extraction --- p.22
Chapter 2.4.2. --- Corner Detection --- p.25
Chapter 2.4.3. --- Corner Selection --- p.27
Chapter 2.4.3.1. --- Mouth Corner Pairs Detection --- p.27
Chapter 2.4.3.2. --- Iris Detection --- p.27
Chapter 2.5. --- Experimental Results --- p.30
Chapter 2.6. --- Conclusions --- p.30
Chapter 2.7. --- Notes on Publications --- p.30
Chapter Chapter 3. --- Fiducial Point Extraction with Shape Constraint --- p.32
Chapter 3.1. --- Introduction --- p.32
Chapter 3.2. --- Statistical Theory of Shape --- p.33
Chapter 3.2.1. --- Shape Space --- p.33
Chapter 3.2.2. --- Shape Distribution --- p.34
Chapter 3.3. --- Shape Guided Fiducial Point Localization --- p.38
Chapter 3.3.1. --- Shape Constraints --- p.38
Chapter 3.3.2. --- Intelligent Search --- p.40
Chapter 3.4. --- Experimental Results --- p.40
Chapter 3.5. --- Conclusions --- p.42
Chapter 3.6. --- Notes on Publications --- p.42
Chapter Chapter 4. --- Statistical Pattern Recognition --- p.43
Chapter 4.1. --- Introduction --- p.43
Chapter 4.2. --- Bayes Decision Rule --- p.44
Chapter 4.3. --- Gaussian Maximum Probability Classifier --- p.46
Chapter 4.4. --- Maximum Likelihood Estimation of Mean and Covariance Matrix --- p.48
Chapter 4.5. --- Small Sample Size Problem --- p.50
Chapter 4.5.1. --- Dispersed Eigenvalues --- p.50
Chapter 4.5.2. --- Distorted Classification Rule --- p.55
Chapter 4.6. --- Review of Methods Handling the Small Sample Size Problem --- p.57
Chapter 4.6.1. --- Linear Discriminant Classifier --- p.57
Chapter 4.6.2. --- Regularized Discriminant Analysis --- p.59
Chapter 4.6.3. --- Leave-one-out Likelihood Method --- p.63
Chapter 4.6.4. --- Bayesian Leave-one-out Likelihood method --- p.65
Chapter 4.7. --- Proposed Method --- p.68
Chapter 4.7.1. --- A New Covariance Estimator --- p.70
Chapter 4.7.2. --- Model Selection --- p.75
Chapter 4.7.3. --- The Mixture Parameter --- p.76
Chapter 4.8. --- Experimental results --- p.77
Chapter 4.8.1. --- Implementation --- p.77
Chapter 4.8.2. --- Results --- p.79
Chapter 4.9. --- Conclusion --- p.81
Chapter 4.10. --- Notes on Publications --- p.82
Chapter Chapter 5. --- Conclusions and Future works --- p.83
Chapter 5.1. --- Conclusions and Contributions --- p.83
Chapter 5.2. --- Future Works --- p.84
26
Wang, Qi. "Nonlinear noise compensation in feature domain for speech recognition with numerical methods /." 2004. http://wwwlib.umi.com/cr/yorku/fullcit?pMQ99403.
Full textAbstract:
Thesis (M.Sc.)--York University, 2004. Graduate Programme in Computer Science.Typescript. Includes bibliographical references (leaves 60-65). Also available on the Internet. MODE OF ACCESS via web browser by entering the following URL: http://wwwlib.umi.com/cr/yorku/fullcit?pMQ99403
27
Moodley, Deshendran. "Artificial neural networks for image recognition : a study of feature extraction methods and an implementation for handwritten character recognition." Thesis, 1996. http://hdl.handle.net/10413/6094.
Full textAbstract:
The use of computers for digital image recognition has become quite widespread.
Applications include face recognition, handwriting interpretation and fmgerprint analysis.
A feature vector whose dimension is much lower than the original image data is used to
represent the image. This removes redundancy from the data and drastically cuts the
computational cost of the classification stage. The most important criterion for the
extracted features is that they must retain as much of the discriminatory information
present in the original data. Feature extraction methods which have been used with neural
networks are moment invariants, Zernike moments, Fourier descriptors, Gabor filters and
wavelets. These together with the Neocognitron which incorporates feature extraction
within a neural network architecture are described and two methods, Zernike moments and
the Neocognitron are chosen to illustrate the role of feature extraction in image recognition.Thesis (M.Sc.)-University of Natal, Pietermaritzburg, 1996.
28
Chung, Pei-Ju, and 鍾沛儒. "Applying Facial Action Units and Feature Selection Methods to Develop the Learning Emotion Image Database and Recognition Model." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/tj8335.
Full textAbstract:
碩士國立中興大學
資訊管理學系所
106
Emotion is the psychological state that human are exposed to various events. The psychological state is closely related to the physical state and it is a variety of physiological signals. Researchers judge human mental states by capturing and analyzing physiological signals. The classification of emotions is quite diverse. From basic emotions that are inborn and universally applicable to the acquisition of highly interactive and complex emotions from various social situations in the acquired growth, scholars are involved in research. In various contexts, learning-related emotions are more valued. Emotions affect student learning, and learning effectiveness can also reflect student emotions. We focuses on the latter. Learning emotions is to explore the emotional state of students in the learning process. Researchers will start with basic emotions when discussing issues related to learning emotions, because basic emotions are easily defined by intuition. Ekman analyzes the movement of facial muscles when humans express basic emotions around the world as an action unit and explains its connection with basic emotions. After learning the basic emotions through the action unit coding system, the researchers wanted to analyze complex learning emotions through action units. However, we found that different studies have different action units for learning emotions. Therefore, we decided to find out the correlation between learning emotions and action units. First, we will establish a database named as “Learning Emotion Image Database” and operational definition. Labeling learning emotions and action units according to the operational definition as the training data. Then, three feature selection methods are used: decision tree, GA+SVM and ReliefF algorithm to find out the relationship between action units and learning emotions. Under the binary classification, we research the correlation between individual emotions and action units. The results showed the common AU combination of the three feature selection methods. Compared with different studies, although single action units have significant correlation with learning emotions, AU combinations can more accurately identify learning emotions. Under the multiclass classification, we research the accuracy of learning emotion recognition. The results showed that with the same accuracy, GA+SVM will have the smallest AU combination. The decision tree grabs more AU and speculates that there may be overfitting. The AU combination generated by ReliefF algorithm is different from both of them. Because the ReliefF algorithm does not consider the correlation between features and features, only the statistical correlation between the features and target categories is calculated. It cannot effectively remove redundant features. In order to apply to the actual teaching scene, we establishes the action unit recognition model to achieve the instant recognition of learning emotion. The action unit recognition model which apply random forest classification algorithm uses feature values as input vectors to predict action units. After training and testing with Learning Emotion Image Database and CK+ database, the results show that 15 action units we used in the learning emotion model, most of them have good generalization ability and the model has good discrimination. A few action units have poor generalization ability. Finally, the action unit identification model is used to obtain the action unit, and the learning emotion recognition model is used to identify the learning emotion generated by the learner in the learning process, so as to instantly recognize learning emotion.
29
Sun, Rui-Qiang, and 孫瑞強. "A Conspicuous-Feature-based Face Recognition method." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/24223069254264992394.
Full textAbstract:
碩士國立高雄應用科技大學
電子工程系
97
Face recognition got more high attention in these years, but current method for recognition always takes the whole face as the main feature, such as PCA and LDA. However, further analysis on the five senses of human face in database is not made in those methods in consideration of representation. The idea of conspicuous features is proposed in this paper and utilized for investigating the conspicuousness of five senses in each man. For example: The eye is a characteristic. In a crowd of big eyes person, somebody with small eyes manipulates the prominent characteristic. With this characteristic, this person could be recognized quickly according to this distinguishing feature. Based on this idea, we use the conspicuous features, and extract the characteristic using Gabor Wavelet Filter (GWF). Meanwhile, Genetic Algorithms method (GA) is used for simplifying the GWF characteristic. The reason for reducing the characteristic dimension is because GWF would amplify the characteristic 40 times, and then weighting on these conspicuous features is used for assisting face recognition.
30
Huang, Zhao-Shi, and 黃昭世. "Research on speech recognition system-using multi-feature recognition method." Thesis, 1987. http://ndltd.ncl.edu.tw/handle/73821767331352416215.
Full text
31
Kharchenko, A. "Features of development of sign language recognition methods." Thesis, 2021. https://openarchive.nure.ua/handle/document/17988.
Full text
32
Chu, Pei-Yuan, and 朱培源. "Face Recognition Using Facial Feature Based on Decision Method." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/56388276463917342120.
Full textAbstract:
碩士義守大學
資訊管理學系
101
Face recognition application has penetrated all levels, such as access control systems, smart appliances and robot recognition. Commonly used face recognition method includes principal component analysis, linear discriminant analysis and facial features analysis method. Facial features to recognize faces mainly uses relative size of facial shape and location characteristics to identify whether their identification is a critical success factor lies in the accuracy of facial shapes made, how to choose a good number of features and how to combine the characteristics of the last and with the appropriate decision rule. Basically, there are many facial features can be selected, so how to assemble features and establish decision rules becomes very important. The thesis proposes a new set of decision rules used in facial feature. In the thesis, the characteristics of the initial selection are 32 features, and this similarity lowest images are eliminated by taking advantage of the 32 features, the images with different expressions or other images from different angles with the same person are also eliminated by using the images mentioned above. Finally, it selects a valid combination among the 32 characteristic features and decides the higher probability candidate images through the statistics method and calculation of deviation. Experimental results showed that if we only select one candidate image, correct judgment of the proposed method is about 90% in this thesis. If the candidate selected four images, the correct judgment was 100%.
33
Chen, Chun-wei, and 陳俊瑋. "A SVM Face Recognition Method Based on Gabor Feature Extraction." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/ryw274.
Full textAbstract:
碩士國立臺灣科技大學
電機工程系
94
The study in biometrics field has vigorous development these years, especially in feature-based recognition field. Since the September 11 attacks, there are more and more specialists dig into biometrics field to develop a security system to guard against the horror attacks; therefore, the study in face recognition has become one popular method in biometrics researches. However, the face recognition is the not easy to reach high recognition rate even though it is the most intuitional method. It is a good way to extract features by using Gabor filter, especially in finger print recognition and face recognition. The statistical learning theory is a hot topic these decades. The neural network has been used in many applications and has performed very well. These years, the support vector machine has showed its good classification ability and there are many papers proved that it performs better than neural network in some applications such as biometrics recognition, document classification, and data mining. In this thesis, I built a MATLAB GUI based security platform. This platform combines Gabor feature extraction, SVM classification, and duo-threshold concepts to simulate the real-world security system. While using the SVM classifiers, I adopted one-against-rest method instead of one-against-one method because the former one has better exclusivity.
34
Chen, Jian-rong, and 陳建榮. "Low-Resolution Facial Components based Feature Extraction Method for Facial Expression Recognition." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/rvcdaw.
Full textAbstract:
碩士國立臺灣科技大學
電機工程系
99
Facial expression is a non-verbal communication media, which plays an important role in daily life. People often switch emotions and other emotional reactions according to the surrounding environment and the psychological feelings. This thesis aims to develop an automatic facial expression recognition system which can detect human faces, extract features, and recognize the corresponding expressions. In face detection phase, the Adaboost learning algorithm is applied to select the appropriate Haar-like features, and combine all weak classifiers with different weights to form a strong classifier for detecting face. In feature extraction, each detected face image is divided into three local images such as eye, eyebrow and mouth based on organ location, and which are used to form the first layer areas. Then, the original face image and the local images are down-sampled to form the second layer areas. Subsequently, the Local Binary Pattern (LBP) and the Discrete Cosine Transform (DCT) operators are applied on the two types of areas to extract the texture information and the noise-free low frequency information. The recognition stage is based on the well-known SVM classifier. The extracted global/local information from DCT coefficients and LBP histograms is transformed to expression feature vector and then fed to the SVM classifier for facial expression recognition. In this thesis, the proposed expression classification scheme recognizes seven various facial expressions, such as happy, angry, sad, surprise, fear, disgust and neutral with the JAFFE database. In the experimental results, the proposed method can yield superior performance compared to former approaches even with image of lower resolutions. Finally, the equipments used in this research including PTZ camera, USB video capture card, notebook and RS232 transmission. These equipments realize the proposed automatic facial expression recognition system, and which can be considered as an effective candidate for the surveillance applications.
35
LI, ROU-YI, and 李柔誼. "Image Recognition Method Based on Edge Features and Artificial Neural Network." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/u34qgr.
Full textAbstract:
碩士國立高雄科技大學
機械工程系
107
This study image feature recognition is based on the edge line.Two methods are proposed for image recognition in the study.The first is a sample comparison, and the second is a neural network training.Both methods use text modeling blocks to test samples.The image edge feature is created by the gradient after the binarized image.In the sample comparison, the edge features of the sample must be established first.Find the gradient of the each pixel,and use the edge feature of the sample and the gradient angle of the image to judge the similarity.In the neural network, it is performed based on the image edge features of the training data.In order to highlight the edge features of the image, this study trains the pixel position, the X and Y direction gradient of the edge feature pixel .Thereby improving the recognition rate of image recognition. Learned from the experimental results.Both pattern recognition methods are not limited by the text modeling blocks pattern, the position and placement direction.The average recognition rate of the edge feature sample comparison method is 98%.The average recognition rate of the edge feature neural network is 59%.Because the neural network identification rate of the edge feature is low, this study attempts to perform neural network training based on HSV and RGB value in the pixel, image binarization, grayscale value as training data.The recognition rates are 79%, 88%, 96%, and 88%, respectively.Among them, HSV is the best.
36
Mu-Cun, Lu, and 呂木村. "A Feature Point Filtering and Choosing Method for the Visually Impaired Recognition System." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/72f8re.
Full textAbstract:
碩士國立臺北科技大學
資訊工程系所
104
In our previous work, we presented a wearable system for visually impaired’s inconvenient in their daily life. The system can recognize signboard, daily commodities and detect obstacle. The feature of daily commodities identification recognize object by SURF(Speeded-Up Robust Features) algorithm which has scale and rotation invariant. However, when the system extract feature points from the object, it doesn’t know if the object is suitable for recognition, but store the feature points straightly to the database. The situation cause some of objects can’t be recognized easily or unrecognized. Furthermore, when the number of objects increase, the database of the feature points is getting larger. The database include repeated feature point which will influence the performance of recognition. Therefore, this paper propose a mechanism of feature point filter aim to reduce the number of feature points efficiently. The system is divided into four steps: (1) using the density of feature points exclude the objects which is unsuitable for recognition objects, (2) using feature matching method exclude inter and intra of similar feature points, (3) using the scale of feature points to select the representative feature points, (4) using position distribution of feature points to get more uniform result, also more stable matching result. According to the experimental results, the number of feature points can exclude more than 50% and the feature matching performance can improve 30% without sacrifice recall and precision rate. Finally, we design the system of feature point filter that provide the normal sighted person build object information for visually impaired. The system can get message feedback when we build object information.
37
Zhuang, Zhen-Cun, and 莊振村. "An efficient Chinese character recognition method based on hashing of structural feature codes." Thesis, 1993. http://ndltd.ncl.edu.tw/handle/88994741988469459534.
Full text
38
Zhou, Yun-Sheng, and 周昀昇. "The Study of 3D Geometric Feature Recognition Method on Robot Automatical Assembly Task." Thesis, 1997. http://ndltd.ncl.edu.tw/handle/16052863429408454819.
Full text
39
Tvoroshenko, I., and K. Temchur. "Features of software application development for food recognition using deep machine learning methods." Thesis, 2021. https://openarchive.nure.ua/handle/document/16084.
Full text
40
Liang, Hau-Yun, and 梁皓雲. "A Hybrid Method for Face Recognition based on Block-Based Facial Features." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/qeqyta.
Full textAbstract:
碩士國立中央大學
資訊工程研究所
94
The relevant research of face recognition has have to be strengthen and overcome rate of accuracy of recognition. The previous treatment steps and content of input image obviously affect accuracy of recognition. The so-called content of image means that the environment and the changes of lighting on face, and this factor affects the rate of recognition very deeply. Most previous research focus on taking whole face image for recognition. This thesis focuses on dividing the face image into different areas, then takes these different areas to recognize. The face image is often full of skin areas, which have less help to recognition but damage. Furthermore, the color of skin areas is easily influenced by the lighting condition or changes of the environment. In order to prevent the above drawbacks which may decrease the accuracy of face recognition, the paper propose a method which fetches different areas of the face as features and these areas have little skin color areas . The algorithm of face recognition consists of LDA + PCA and before recognition we must first do wavelet transform on the image. The reason doing wavelet transform is to keep the changeless parts of image, in other words it can remove some unnecessary parts of image. In addition, the size of image will dwindle too, so the time to recognize will be reduced. After finishing of recognition, due to several areas to recognize, several results of recognition will be produced. So generally speaking in combining these result of recognition, people usually adopts the vote method, but in addition to voting method, we also adopted weighting approach in this thesis. The weight value was based on the results of features which were clustered. We adopt weighting method when the vote method is unable to decide. The experimental results showed that our proposed approach which is based on certain blocks in the face is better than other methods which using the entire face image in accuracy rate.
41
Huang, Sheng-Yu, and 黃盛裕. "A Study of Emotion Recognition Based on a Novel Triangular Facial Feature Extraction Method." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/15945778906315327037.
Full textAbstract:
碩士國立成功大學
資訊工程學系碩博士班
97
Emotions play major roles in human computer interaction, and emotion recognition system is often encountered in distance education, children education, health care, even some pervasive computing applications. In this paper, we propose a novel triangular facial feature extraction method to recognize emotions, also define a fitness function suitable for facial emotion recognition, and at the end we use Genetic Algorithm to determine the optimal facial features. In the preprocessing part, we use modified Active Shape Model (ASM) to extract facial feature points to avoid environmental conditions, and also extract representative triangular facial features. We adopt various machine learning methods to evaluate the proposed method experimenting on the JAFFE and eNTERFACE data sets for recognizing seven and six emotions respectively. The experimental results show that based on the statistical features 65.1% recognition rate was achieved in the JAFFE data set and 50% in the eNTERFACE data set, and based on the defined fitness function 70.2% recognition rate was achieved in the JAFFE data set and 56.7% in the eNTERFACE data set. It can increase about 5% recognition rate based on the fitness function we proposed in these two data sets.
42
TIEN, SHAO-HUA, and 田韶華. "Fingerprint Recognition Method Based on Fusion of Spatial Statistical Features and Minutia Matching." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/x98wy4.
Full textAbstract:
碩士國立中央大學
資訊工程學系在職專班
103
Product get smaller and technological improve every day, relatively small area of the fingerprint sensor to capture the DPI is also getting smaller and smaller, resolution or image complexity will affect the image of the fingerprint identification result, the traditional approach has been to identify a single one inadequate use of feature points presented in this recognition and non-recognition feature points plus two kinds of identification method to fusion, non-feature point identification method uses a statistical and probability neural network, coupled with training through fingerprint classification to achieve their goals in decision fusion experiments on the max and two-stage and other fusion methods, and finally decision fusion experiment error rate lower than the previous two individual identification party.
43
Lo, Pai-Ling, and 羅百玲. "An Unsupervised Pattern Recognition Method for Identifying TFBS Based on DNA Short Sequence Features." Thesis, 2006. http://ndltd.ncl.edu.tw/handle/enb329.
Full textAbstract:
碩士國立臺灣科技大學
資訊工程系
94
Identifying binding sites for the transcription factor in the upstream sequences of genes to which the factor binds is the first step to understand the gene regulatory mechanism. Recent assessment of computational tools for identifying these binding sites indicates that identifying these regulatory elements remains a challenging task in higher organisms, such as the human species. The task is limited in the intrinsic subtlety of binding sites and the huge background noise. That is, only a small portion of genome will be bound by transcription factors and sequence-specific recognition for binding is subtle. In this thesis, we proposed an unsupervised pattern recognition method to handle the incomplete and unbalanced biological data. To model the binding activity, a vector of small sequence features was proposed. To identify candidate pattern for binding sites, the overall over-representative and sequence popularity of each pattern are taken into consideration in ranking. To evaluate the performance and to compare with related work, a benchmark which has been used to assess existing tools was adopted. The experimental results show that the proposed methodology outperforms the related work in terms of the nucleotide level performance when we only consider the top 3 nodes in the ranking. The proposed representation of binding sites and the ranking mechanism make efficient predictions of binding sites.
44
Tvoroshenko, I., and Y. Bielinskyi. "Features of methods of issuation of key areas and vector recognition of manuscript symbols on the image." Thesis, 2021. https://openarchive.nure.ua/handle/document/17955.
Full text
45
BALLAN, LAMBERTO. "Object and event recognition in multimedia archives using local visual features." Doctoral thesis, 2011. http://hdl.handle.net/2158/485661.
Full text
46
He, Sheng-Yu, and 何勝宇. "SIFT Features and Machine Learning based Sclera Recognition Method with Efficient Sclera Segmentation for Identity Identification." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/n5x33k.
Full textAbstract:
碩士國立中興大學
電機工程學系所
106
The identity identification has been an important issue in recent years. Compared with the traditional identification system by using magnetic buckle, access card or other mediums, the biological features have higher safety and protection from counterfeit. The blood vessels on sclera have high uniqueness, and the individual’s vascular patterns are grown in different shape. As time goes on, these blood vessel textures became stable, and can be used as the identify identities medium. Base on sclera veins features, an identity recognition algorithm is proposed in this thesis. The proposed algorithm is partitioned into three stages for processing. The first stage is preprocessing, which includes pupil locating, iris segmentation, and sclera segmentation. The proposed method will locate the center coordinate of the pupil in order to decrease the calculate amount when the iris segmentation is active, and the process can help to achieve the goal to decrease the time complexity and increase the segmentation accuracy. To promote the performance, the iris segmentation process applies the improved Daugman algorithm to select the region of interested, down sampling the image ratio, and consider the circumference of sector. The result reveals that the iris segment rate reaches up to 99.51%. In the sclera segmentation process, by utilizing the low saturation property, the preliminary sclera contour can be achieved, the convex hull is calculated, and then the appropriate region is detected by setting the seed points. Thus, the sclera segment rate is up to 98.35%. At the second stage, by using the scale-invariant feature transform (SIFT) method, the blood vessel features are extracted after the image enhancement. Next, by using the K-means algorithm, the proposed system gathers the similar features together to construct a codebook to describe the interested features. The eye images will refer the codebook to get the histogram of main features, and then feed the main features into the support vector machine (SVM) to train a classifier. The last stage is used for the validation. To predict the category of testing dataset, the result shows that the accuracy reaches up to 98% if the training data have forty categories or more.
47
Cheng, Yu-Lin, and 鄭煜霖. "The investigation of speech recognition in Mandarin word by using the method of principle component with various feature numbers." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/33596933637327137943.
Full textAbstract:
碩士國立中興大學
統計學研究所
103
This paper focuses on non-specific speaker to discuss the recognition for the 1391 consonant, vowels and mandarin of recognition. The recognition process can mainly separate into three parts: First, we make the vocal data doing fore-process, such as endpoint detecting and frame cutting. Secondly, transform it into feature by Mel-frequency cepstrum coefficient. Finally construct the speech model by the method of K-means algorithm and principal component analysis. The main purpose of this paper is to find the optimal number of features to achieve the highest recognition rate. The experiment of speech database is recorded by eighteen different speaker (total 250,380 tones). Through experiments, the optimal result is obtained as the number is 20 of K-means algorithm of the center, the number is 36 of features, consonant highest recognition rate is 88.13%; and the number is 15 of the center, the number is 30 of features, vowel highest recognition rate is 86.73%; finally the number is 20 of the center, the number is 36 of features, the weights of consonant and vowel are 0.6 and 0.4, mandarin highest recognition rate is 78.54%. Keywords: K-means algorithm, Principal component analysis
48
Sheu, Chung-Chieh, and 徐仲杰. "A handwritten chinese characters recognition method based on primitive and fuzzy features via SEART neural net model." Thesis, 1995. http://ndltd.ncl.edu.tw/handle/92946634800767476278.
Full textAbstract:
碩士國立臺灣科技大學
工程技術研究所
83
A handwritten Chinese characters recognition method using SEART neural network model with primitive and compound fuzzy features is proposed. The primitive features are extracted in local and global view. Also they have good stability. Since the writings of handwritten Chinese characters vary a lot, we adopt fuzzyract the compound features in structural view. These categories of features are extracted in one pass, so thel effort is not heavy. We combine the two categories of features and use a fast classifier, named supervised extended ART (SEART) neural network model, to recognize the handwritten Chinese characters. The SEART classifier has excellent performance, fast, good generalization and exceptions handling ability in complex problems. Using the fuzzy set theory in features extraction and the neural network as a classifier are helpful for tolerating distortions, noises and variations. In spite of the poor thinning, an average of 90.24% recognition rate on the 605 test characters is obtained. The database used is HCCRBASE (provided by CCL, ITRI, Taiwan). It not only confirms the feasibility of the proposed system, but also suggests that applying the fuzzy set theory and neural networks on HCCR is an efficient and promising approach.
49
Figueiredo, Joana Sofia Campos. "Assistive locomotion strategies for active lower limb devices." Master's thesis, 2015. http://hdl.handle.net/1822/39613.
Full textAbstract:
Dissertação de mestrado integrado em Engenharia Biomédica (área de especialização em Eletrónica Médica)In order to actively aid or restore legged locomotion to individuals suffering from muscular impairments, weakness or neurologic injury, rehabilitation is recommended as a more appropriate way to achieve the ultimate goal of a continuous ambulatory monitoring. Also, the assistance with wearable robots (WRs) during daily living activities provides a more intensive and purposeful targeted therapeutic training, and also reduces the treatment cost and the number of health care personnel. Thus, it is crucial the development of locomotion strategies that recognize in real-time the locomotion mode of human-robot interaction in overground daily living activities. Thus, this thesis intends to develop two locomotion strategies which will be integrated in high level control of exoskeleton H2 (Exo-H2), the WR developed under the scope of BioMot project. The first locomotion strategy proposed and validated addresses online detection of events and gait phases uniquely through information from embedded sensors. This knowledge will allow determining in real-time the biomechanical parameters of assisted walking, and consequently to assess the progress of rehabilitation process by means of WR. The solution validation in different locomotion conditions (assisted walking by WR, walking of humanoid robot and walking of healthy subject) shows up that the proposed solution led to a robust and general tool for gait detection, which is also capable to detect more events and gait phases comparatively to the works presented in literature. Locomotion mode recognition is the second locomotion strategy developed in this thesis, which allows the recognition of different locomotion modes. Based on an exhaustive state of the art survey, a more robust and accurate procedure that leads to a more robust and accurate tool was delineated. According to the results achieved for offline scenario it was verified that the performance of the locomotion strategy increases by using different types of biomechanical parameters, which should be previously selected by means of multivariate statistic methods. Both binary and multiclass classification were addressed through support vector machine (SVM). The implementation of these methods led to a powerful and accurate tool of offline recognition of locomotion modes. Additionally, a strategy for online recognition was proposed. Further work will consist on the application of these locomotion strategies in real-time environment of gait rehabilitation.
De forma a apoiar ou a restaurar a locomoção de indivíduos que apresentam fraqueza muscular ou doenças neurológicas, a reabilitação é recomendada como a forma mais apropriada para alcançar uma monitorização ambulatória contínua. Além disso, a assistência com robots ambulatório (RA) durante as atividades diárias promove um treino terapêutico mais intensivo e direcional, assim como também reduz os custos de tratamento e o número de profissionais de saúde. Como tal, é crucial o desenvolvimento de estratégias que reconheçam, em tempo real, o modo de locomoção da interação sujeito-robot durante as atividades quotidianas. Assim, esta tese visa desenvolver duas estratégias de locomoção, as quais serão integradas no controlo de alto nível do Exo-H2, que corresponde ao RA desenvolvido no âmbito do projeto BioMot. A primeira estratégia de locomoção proposta e validada consiste na deteção online dos eventos e fases da marcha, usando exclusivamente a informação fornecida pelos sensores embebidos. Este conhecimento permitirá a determinação em tempo real dos parâmetros biomecânicos da marcha assistida, e por conseguinte permitirá avaliar o progresso da reabilitação. A validação da solução proposta em diferentes contextos de locomoção (marcha assistida por RA, marcha de um robot humanoide e a marcha de um sujeito saudável) revelou que esta constitui uma ferramenta robusta e geral para a deteção da marcha, sendo capaz de detetar mais eventos e fases da marcha comparativamente aos estudos apresentados na literatura. O reconhecimento do modo de locomoção é a segunda estratégia desenvolvida nesta tese, a qual permite o reconhecimento de diferentes modos de locomoção. Com base no exaustivo levantamento do estado da arte, foi delineado um procedimento robusto, que conduziu a uma ferramenta mais robusta e precisa. De acordo com os resultados alcançados para o cenário offline verificou- se que o desempenho desta estratégia de locomoção aumenta com a utilização de diferentes tipos de parâmetros biomecânicos, os quais devem ser previamente selecionados por meio de métodos estatísticos. Tanto a classificação binária, como a classificação de multi-classes, foram implementadas através do support vector machine (SVM). A implementação destes métodos conduziu a uma ferramenta precisa de reconhecimento dos modos de locomoção em offline. Além disso, também foi proposta a estratégia para o reconhecimento em tempo real. Como trabalho futuro propõe-se a aplicação destas estratégias de locomoção no ambiente em tempo real de reabilitação da marcha.
50
Elmi, Carlo Alberto. "Design system integration for multi-objective optimization of aero engine combustors." Doctoral thesis, 2022. http://hdl.handle.net/2158/1276939.
Full textAbstract:
The transformation towards a climate-neutral civil aviation is providing significant business opportunities to the aero engine market players. To meet this target and keep competitiveness, however, groundbreaking solutions must be introduced at the product’s level in the shortest possible time. Industry lead-ers are increasingly embracing lean and digital approaches for this purpose, by applying these concepts at all company’s levels. Considerable room for im-provements can be identified in the development of complex components as, for instance, the combustor. Due to the complexity of phenomena taking place and interacting into it, there are conflicting functional requirements defined over different physical domains. This leads to a design approach that must be both multidisciplinary and multi-objective, in which the need for supporting know-how and product expertise arises with extensive and structured studies of the design space arises. Nowadays, simulation-based methodologies repre-sent a standard in evaluating multiple configurations of the system, although it may lead to heterogeneous models interacting with each other, sharing miscel-laneous information within the process. In this context, taking advantage of in-tegrated design systems has been proven to be beneficial in standardizing the simulation processes while embedding design’s best practices.
The subject matter of this work is the Combustor Design System Integra-tion (DSI), an integrated methodology aimed at easing and streamlining the preliminary design phase of aero engine combustors. Its concept will be de-scribed in the first part, where the automation of low value-added tasks will be introduced together with four custom integrated tools. It is composed of a CAD generation system, a RANS-based CFD suite for reactive flow calculations, a boundary-conditions processor for 3D thermal FEA and a FE structural envi-ronment for stress and displacement estimation. Particular importance is given to the definition of cooling and quenching systems on combustor’s liners, since their prominent impact on aero-thermal and durability performance. Therefore, specific features for a detailed topological management of holes are presented in this work, providing advance patterning and arrangement capabilities which are not addressed in other design systems. Finally, it will be possible to prove the reduction of lead time for analysis, as well as the enhancement of the overall process robustness. The NEWAC combustor, a lean-burn concept developed in the context of the homonymous European research project, will be exploited as a case allowing, moreover, an assessment of the DSI modelling approach. In the second part will be presented a dedicated framework for multi-objective design optimization, comprising the DSI tools for CAD generation and CFD analysis. A fully automated and water-tight process is here implemented in order to ad-dress the combustor’s problem of dilution mixing, aimed at optimizing the temperature profiles and the emission levels at its outlet. This approach will leverage on advanced neural network algorithms for improving the overall de-sign workflow, so to ensure that the optimal combustor configuration is de-fined as a function of the product’s Critical-To-Quality. The results of the opti-mization will be shown for a rich-quench-lean combustor concept intentionally designed to support this activity, referred as to LEM-RQL.
The general intention of this work, in the end, is to demonstrate how in-tegrated design systems embedded in optimization frameworks could repre-sent both a strategic asset for industry players and a relevant topic for academ-ics. Given the pervasive integration-and-automation of the process, the general-ity in processing multiple design layouts and the possibility to accommodate increasingly advanced and sophisticated optimization algorithms, the DSI pro-cedure configure itself as an ideal platform within the technology maturation process, thus enabling not only the improvement of in-service components but also the development of next-generation combustor products.