Local Binary Patterns in Focal-Plane Processing. Analysis and Applications

Feature extraction is the part of pattern recognition, where the sensor data is transformed into a more suitable form for the machine to interpret. The purpose of this step is also to reduce the amount of information passed to the next stages of the system, and to preserve the essential information in the view of discriminating the data into different classes. For instance, in the case of image analysis the actual image intensities are vulnerable to various environmental effects, such as lighting changes and the feature extraction can be used as means for detecting features, which are invariant to certain types of illumination changes. Finally, classification tries to make decisions based on the previously transformed data. The main focus of this thesis is on developing new methods for the embedded feature extraction based on local non-parametric image descriptors. Also, feature analysis is carried out for the selected image features. Low-level Local Binary Pattern (LBP) based features are in a main role in the analysis. In the embedded domain, the pattern recognition system must usually meet strict performance constraints, such as high speed, compact size and low power consumption. The characteristics of the final system can be seen as a trade-off between these metrics, which is largely affected by the decisions made during the implementation phase. The implementation alternatives of the LBP based feature extraction are explored in the embedded domain in the context of focal-plane vision processors. In particular, the thesis demonstrates the LBP extraction with MIPA4k massively parallel focal-plane processor IC. Also higher level processing is incorporated to this framework, by means of a framework for implementing a single chip face recognition system. Furthermore, a new method for determining optical flow based on LBPs, designed in particular to the embedded domain is presented. Inspired by some of the principles observed through the feature analysis of the Local Binary Patterns, an extension to the well known non-parametric rank transform is proposed, and its performance is evaluated in face recognition experiments with a standard dataset. Finally, an a priori model where the LBPs are seen as combinations of n-tuples is also presented

Classification of brain tumor extracts by high resolution ¹H MRS using partial least squares discriminant analysis

High resolution proton nuclear magnetic resonance spectroscopy (¹H MRS) can be used to detect biochemical changes in vitro caused by distinct pathologies. It can reveal distinct metabolic profiles of brain tumors although the accurate analysis and classification of different spectra remains a challenge. In this study, the pattern recognition method partial least squares discriminant analysis (PLS-DA) was used to classify 11.7 T ¹H MRS spectra of brain tissue extracts from patients with brain tumors into four classes (high-grade neuroglial, low-grade neuroglial, non-neuroglial, and metastasis) and a group of control brain tissue. PLS-DA revealed 9 metabolites as the most important in group differentiation: γ-aminobutyric acid, acetoacetate, alanine, creatine, glutamate/glutamine, glycine, myo-inositol, N-acetylaspartate, and choline compounds. Leave-one-out cross-validation showed that PLS-DA was efficient in group characterization. The metabolic patterns detected can be explained on the basis of previous multimodal studies of tumor metabolism and are consistent with neoplastic cell abnormalities possibly related to high turnover, resistance to apoptosis, osmotic stress and tumor tendency to use alternative energetic pathways such as glycolysis and ketogenesis.

Design and implementation of machine vision system for the mobile assembly robot

The review of intelligent machines shows that the demand for new ways of helping people in perception of the real world is becoming higher and higher every year. This thesis provides information about design and implementation of machine vision for mobile assembly robot. The work has been done as a part of LUT project in Laboratory of Intelligent Machines. The aim of this work is to create a working vision system. The qualitative and quantitative research were done to complete this task. In the first part, the author presents the theoretical background of such things as digital camera work principles, wireless transmission basics, creation of live stream, methods used for pattern recognition. Formulas, dependencies and previous research related to the topic are shown. In the second part, the equipment used for the project is described. There is information about the brands, models, capabilities and also requirements needed for implementation. Although, the author gives a description of LabVIEW software, its add-ons and OpenCV which are used in the project. Furthermore, one can find results in further section of considered thesis. They mainly represented by screenshots from cameras, working station and photos of the system. The key result of this thesis is vision system created for the needs of mobile assembly robot. Therefore, it is possible to see graphically what was done on examples. Future research in this field includes optimization of the pattern recognition algorithm. This will give less response time for recognizing objects. Presented by author system can be used also for further activities which include artificial intelligence usage.

Cognitive set, absorption, and achievement as moderators of the perceptual closure effect in picture priming /

The present study examined individual differences in Absorption and fantasy, as well as in Achiievement and achievement striving as possible moderators of the perceptual closure effect found by Snodgrass and Feenan (1990). The study also examined whether different instructions (experiential versus instrumental) interact with the personality variables to moderate the relationship between priming and subsequent performance on a picture completion task. 1 28 participants completed two sessions, one to fill out the MPQ and NEO personality inventories and the other to complete the experimental task. The experimental task consisted of a priming phase and a test phase, with pictures presented on a computer screen for both phases. Participants were shown 30 pictures in the priming phase, and then shovm the 30 primed pictures along with 30 new pictures for the test phase. Participants were randomly assigned to receive one of the two different instruction sets for the task. Two measures of performance were calculated, most fragmented measure and threshold. Results of the present study confirm that a five-second exposure time is long enough to produce the perceptual closure effect. The analysis of the two-way interaction effects indicated a significant quadratic interaction of Absorption with priming level on threshold performance. The results were in the opposite direction of predictions. Possible explanations for the Absorption results include lack of optimal conditions, lack of intrinsic motivation and measurement problems. Primary analyses also revealed two significant between-subject effects of fantasy and achievement striving on performance collapsed across priming levels. These results suggest that fantasy has a beneficial effect on performance at test for pictures primed at all levels, whereas achievement striving seems to have an adverse effect on performance at test for pictures primed at all levels. Results of the secondary analyses with a revised threshold performance measure indicated a significant quadratic interaction of Absorption, condition and priming level. In the experiential condition, test performance, based on Absorption scores for pictures primed at level 4, showed a positive slope and performance for pictures primed at levels 1 and 7 based on Absorption showed a negative slope. The reverse effect was found in the instrumental condition. The results suggest that Absorption, in combination with experiential involvement, may affect implicit memory. A second significant result of the secondary analyses was a linear three-way interaction of Achievement, condition and priming level on performance. Results suggest that as Achievement scores increased, test performance improved for less fragmented primed pictures in the instrumental condition and test performance improved for more highly fragmented primes in the experiential condition. Results from the secondary analyses suggest that the revised threshold measure may be more sensitive to individual differences. Results of the exploratory analyses with Openness to Experience, Conscientiousness and agentic positive emotionality (PEM-A) measures indicated no significant effects of any of these personality variables. Results suggest that facets of the scales may be more useful with regard to perceptual research, and that future research should examine narrowly focused personality traits as opposed to broader constructs.

Comparison of classification ability of hyperball algorithms to neural network and k-nearest neighbour algorithms

The main focus of this thesis is to evaluate and compare Hyperbalilearning algorithm (HBL) to other learning algorithms. In this work HBL is compared to feed forward artificial neural networks using back propagation learning, K-nearest neighbor and 103 algorithms. In order to evaluate the similarity of these algorithms, we carried out three experiments using nine benchmark data sets from UCI machine learning repository. The first experiment compares HBL to other algorithms when sample size of dataset is changing. The second experiment compares HBL to other algorithms when dimensionality of data changes. The last experiment compares HBL to other algorithms according to the level of agreement to data target values. Our observations in general showed, considering classification accuracy as a measure, HBL is performing as good as most ANn variants. Additionally, we also deduced that HBL.:s classification accuracy outperforms 103's and K-nearest neighbour's for the selected data sets.

Hyperspectral Mineral Identification using SVM and SOM

Remote sensing techniques involving hyperspectral imagery have applications in a number of sciences that study some aspects of the surface of the planet. The analysis of hyperspectral images is complex because of the large amount of information involved and the noise within that data. Investigating images with regard to identify minerals, rocks, vegetation and other materials is an application of hyperspectral remote sensing in the earth sciences. This thesis evaluates the performance of two classification and clustering techniques on hyperspectral images for mineral identification. Support Vector Machines (SVM) and Self-Organizing Maps (SOM) are applied as classification and clustering techniques, respectively. Principal Component Analysis (PCA) is used to prepare the data to be analyzed. The purpose of using PCA is to reduce the amount of data that needs to be processed by identifying the most important components within the data. A well-studied dataset from Cuprite, Nevada and a dataset of more complex data from Baffin Island were used to assess the performance of these techniques. The main goal of this research study is to evaluate the advantage of training a classifier based on a small amount of data compared to an unsupervised method. Determining the effect of feature extraction on the accuracy of the clustering and classification method is another goal of this research. This thesis concludes that using PCA increases the learning accuracy, and especially so in classification. SVM classifies Cuprite data with a high precision and the SOM challenges SVM on datasets with high level of noise (like Baffin Island).

Étude de la réponse du détecteur ATLAS-MPX aux neutrons rapides

Les détecteurs ATLAS-MPX sont des détecteurs Medipix2-USB recouverts de convertisseurs de fluorure de lithium et de polyéthylène pour augmenter l’efficacité de détection des neutrons lents et des neutrons rapides respectivement. Un réseau de quinze détecteurs ATLAS-MPX a été mis en opération dans le détecteur ATLAS au LHC du CERN. Deux détecteurs ATLAS-MPX de référence ont été exposés à des sources de neutrons rapides 252 Cf et 241 AmBe ainsi qu’aux neutrons rapides produits par la réaction 7Li(p, xn) pour l’étude de la réponse du détecteur à ces neutrons. Les neutrons rapides sont principalement détectés à partir des protons de recul des collisions élastiques entre les neutrons et l’hydrogène dans le polyéthylène. Des réactions nucléaires entre les neutrons et le silicium produisent des particules-α. Une étude de l’efficacité de reconnaissance des traces des protons et des particules-α dans le détecteur Medipix2-USB a été faite en fonction de l’énergie cinétique incidente et de l’angle d’incidence. L’efficacité de détection des neutrons rapides a été évaluée à deux seuils d’énergie (8 keV et 230 keV) dans les détecteurs ATLAS-MPX. L’efficacité de détection des neutrons rapides dans la région du détecteur couverte avec le polyéthylène augmente en fonction de l’énergie des neutrons : (0.0346 ± 0.0004) %, (0.0862 ± 0.0018) % et (0.1044 ± 0.0026) % pour des neutrons rapides de 2.13 MeV, 4.08 MeV et 27 MeV respectivement. L’étude pour déterminer l’énergie des neutrons permet donc d’estimer le flux des neutrons quand le détecteur ATLAS-MPX est dans un champ de radiation inconnu comme c’est le cas dans le détecteur ATLAS au LHC.

L'effort associé à la reconnaissance de la parole chez les adultes et les personnes aînées

L’objectif principal de cette thèse était de quantifier et comparer l’effort requis pour reconnaître la parole dans le bruit chez les jeunes adultes et les personnes aînées ayant une audition normale et une acuité visuelle normale (avec ou sans lentille de correction de la vue). L’effort associé à la perception de la parole est lié aux ressources attentionnelles et cognitives requises pour comprendre la parole. La première étude (Expérience 1) avait pour but d’évaluer l’effort associé à la reconnaissance auditive de la parole (entendre un locuteur), tandis que la deuxième étude (Expérience 2) avait comme but d’évaluer l’effort associé à la reconnaissance auditivo-visuelle de la parole (entendre et voir le visage d’un locuteur). L’effort fut mesuré de deux façons différentes. D’abord par une approche comportementale faisant appel à un paradigme expérimental nommé double tâche. Il s’agissait d’une tâche de reconnaissance de mot jumelée à une tâche de reconnaissance de patrons vibro-tactiles. De plus, l’effort fut quantifié à l’aide d’un questionnaire demandant aux participants de coter l’effort associé aux tâches comportementales. Les deux mesures d’effort furent utilisées dans deux conditions expérimentales différentes : 1) niveau équivalent – c'est-à-dire lorsque le niveau du bruit masquant la parole était le même pour tous les participants et, 2) performance équivalente – c'est-à-dire lorsque le niveau du bruit fut ajusté afin que les performances à la tâche de reconnaissance de mots soient identiques pour les deux groupes de participant. Les niveaux de performance obtenus pour la tâche vibro-tactile ont révélé que les personnes aînées fournissent plus d’effort que les jeunes adultes pour les deux conditions expérimentales, et ce, quelle que soit la modalité perceptuelle dans laquelle les stimuli de la parole sont présentés (c.-à.-d., auditive seulement ou auditivo-visuelle). Globalement, le ‘coût’ associé aux performances de la tâche vibro-tactile était au plus élevé pour les personnes aînées lorsque la parole était présentée en modalité auditivo-visuelle. Alors que les indices visuels peuvent améliorer la reconnaissance auditivo-visuelle de la parole, nos résultats suggèrent qu’ils peuvent aussi créer une charge additionnelle sur les ressources utilisées pour traiter l’information. Cette charge additionnelle a des conséquences néfastes sur les performances aux tâches de reconnaissance de mots et de patrons vibro-tactiles lorsque celles-ci sont effectuées sous des conditions de double tâche. Conformément aux études antérieures, les coefficients de corrélations effectuées à partir des données de l’Expérience 1 et de l’Expérience 2 soutiennent la notion que les mesures comportementales de double tâche et les réponses aux questionnaires évaluent différentes dimensions de l’effort associé à la reconnaissance de la parole. Comme l’effort associé à la perception de la parole repose sur des facteurs auditifs et cognitifs, une troisième étude fut complétée afin d’explorer si la mémoire auditive de travail contribue à expliquer la variance dans les données portant sur l’effort associé à la perception de la parole. De plus, ces analyses ont permis de comparer les patrons de réponses obtenues pour ces deux facteurs après des jeunes adultes et des personnes aînées. Pour les jeunes adultes, les résultats d’une analyse de régression séquentielle ont démontré qu’une mesure de la capacité auditive (taille de l’empan) était reliée à l’effort, tandis qu’une mesure du traitement auditif (rappel alphabétique) était reliée à la précision avec laquelle les mots étaient reconnus lorsqu’ils étaient présentés sous les conditions de double tâche. Cependant, ces mêmes relations n’étaient pas présentes dans les données obtenues pour le groupe de personnes aînées ni dans les données obtenues lorsque les tâches de reconnaissance de la parole étaient effectuées en modalité auditivo-visuelle. D’autres études sont nécessaires pour identifier les facteurs cognitifs qui sous-tendent l’effort associé à la perception de la parole, et ce, particulièrement chez les personnes aînées.

Mesure des champs de radiation dans le détecteur ATLAS et sa caverne avec les détecteurs au silicium à pixels ATLAS-MPX

Les collisions proton-proton produites par le LHC imposent un environnement radiatif hostile au détecteur ATLAS. Afin de quantifier les effets de cet environnement sur la performance du détecteur et la sécurité du personnel, plusieurs simulations Monte Carlo ont été réalisées. Toutefois, la mesure directe est indispensable pour suivre les taux de radiation dans ATLAS et aussi pour vérifier les prédictions des simulations. À cette fin, seize détecteurs ATLAS-MPX ont été installés à différents endroits dans les zones expérimentale et technique d'ATLAS. Ils sont composés d'un détecteur au silicium à pixels appelé MPX dont la surface active est partiellement recouverte de convertisseurs de neutrons thermiques, lents et rapides. Les détecteurs ATLAS-MPX mesurent en temps réel les champs de radiation en enregistrant les traces des particules détectées sous forme d'images matricielles. L'analyse des images acquises permet d'identifier les types des particules détectées à partir des formes de leurs traces. Dans ce but, un logiciel de reconnaissance de formes appelé MAFalda a été conçu. Étant donné que les traces des particules fortement ionisantes sont influencées par le partage de charge entre pixels adjacents, un modèle semi-empirique décrivant cet effet a été développé. Grâce à ce modèle, l'énergie des particules fortement ionisantes peut être estimée à partir de la taille de leurs traces. Les convertisseurs de neutrons qui couvrent chaque détecteur ATLAS-MPX forment six régions différentes. L'efficacité de chaque région à détecter les neutrons thermiques, lents et rapides a été déterminée par des mesures d'étalonnage avec des sources connues. L'étude de la réponse des détecteurs ATLAS-MPX à la radiation produite par les collisions frontales de protons à 7TeV dans le centre de masse a montré que le nombre de traces enregistrées est proportionnel à la luminosité du LHC. Ce résultat permet d'utiliser les détecteurs ATLAS-MPX comme moniteurs de luminosité. La méthode proposée pour mesurer et étalonner la luminosité absolue avec ces détecteurs est celle de van der Meer qui est basée sur les paramètres des faisceaux du LHC. Vu la corrélation entre la réponse des détecteurs ATLAS-MPX et la luminosité, les taux de radiation mesurés sont exprimés en termes de fluences de différents types de particules par unité de luminosité intégrée. Un écart significatif a été obtenu en comparant ces fluences avec celles prédites par GCALOR qui est l'une des simulations Monte Carlo du détecteur ATLAS. Par ailleurs, les mesures effectuées après l'arrêt des collisions proton-proton ont montré que les détecteurs ATLAS-MPX permettent d'observer la désintégration des isotopes radioactifs générés au cours des collisions. L'activation résiduelle des matériaux d'ATLAS peut être mesurée avec ces détecteurs grâce à un étalonnage en équivalent de dose ambiant.

PSWT Based Linear Predictive Coding and Development of a Parallel Multiple Subsequence Structure for DWT Computation

During 1990's the Wavelet Transform emerged as an important signal processing tool with potential applications in time-frequency analysis and non-stationary signal processing.Wavelets have gained popularity in broad range of disciplines like signal/image compression, medical diagnostics, boundary value problems, geophysical signal processing, statistical signal processing,pattern recognition,underwater acoustics etc.In 1993, G. Evangelista introduced the Pitch- synchronous Wavelet Transform, which is particularly suited for pseudo-periodic signal processing.The work presented in this thesis mainly concentrates on two interrelated topics in signal processing,viz. the Wavelet Transform based signal compression and the computation of Discrete Wavelet Transform. A new compression scheme is described in which the Pitch-Synchronous Wavelet Transform technique is combined with the popular linear Predictive Coding method for pseudo-periodic signal processing. Subsequently,A novel Parallel Multiple Subsequence structure is presented for the efficient computation of Wavelet Transform. Case studies also presented to highlight the potential applications.

Classification of Handwritten Characters: Definition, Identification and Utilisation of Regional Characteristics for Lower Case English Characters

A new procedure for the classification of lower case English language characters is presented in this work . The character image is binarised and the binary image is further grouped into sixteen smaller areas ,called Cells . Each cell is assigned a name depending upon the contour present in the cell and occupancy of the image contour in the cell. A data reduction procedure called Filtering is adopted to eliminate undesirable redundant information for reducing complexity during further processing steps . The filtered data is fed into a primitive extractor where extraction of primitives is done . Syntactic methods are employed for the classification of the character . A decision tree is used for the interaction of the various components in the scheme . 1ike the primitive extraction and character recognition. A character is recognized by the primitive by primitive construction of its description . Openended inventories are used for including variants of the characters and also adding new members to the general class . Computer implementation of the proposal is discussed at the end using handwritten character samples . Results are analyzed and suggestions for future studies are made. The advantages of the proposal are discussed in detail .

A Writer Identification System For Handwritten Malayalam Documents

Handwriting is an acquired tool used for communication of one's observations or feelings. Factors that inuence a person's handwriting not only dependent on the individual's bio-mechanical constraints, handwriting education received, writing instrument, type of paper, background, but also factors like stress, motivation and the purpose of the handwriting. Despite the high variation in a person's handwriting, recent results from different writer identification studies have shown that it possesses sufficient individual traits to be used as an identification method. Handwriting as a behavioral biometric has had the interest of researchers for a long time. But recently it has been enjoying new interest due to an increased need and effort to deal with problems ranging from white-collar crime to terrorist threats. The identification of the writer based on a piece of handwriting is a challenging task for pattern recognition. The main objective of this thesis is to develop a text independent writer identification system for Malayalam Handwriting. The study also extends to developing a framework for online character recognition of Grantha script and Malayalam characters

Feature Extraction Methods Based on Linear Predictive Coding and Wavelet Packet Decomposition for Recognizing Spoken Words in Malayalam

Speech signals are one of the most important means of communication among the human beings. In this paper, a comparative study of two feature extraction techniques are carried out for recognizing speaker independent spoken isolated words. First one is a hybrid approach with Linear Predictive Coding (LPC) and Artificial Neural Networks (ANN) and the second method uses a combination of Wavelet Packet Decomposition (WPD) and Artificial Neural Networks. Voice signals are sampled directly from the microphone and then they are processed using these two techniques for extracting the features. Words from Malayalam, one of the four major Dravidian languages of southern India are chosen for recognition. Training, testing and pattern recognition are performed using Artificial Neural Networks. Back propagation method is used to train the ANN. The proposed method is implemented for 50 speakers uttering 20 isolated words each. Both the methods produce good recognition accuracy. But Wavelet Packet Decomposition is found to be more suitable for recognizing speech because of its multi-resolution characteristics and efficient time frequency localizations

classification and content based retrieval of digital mammograms and placental sonograms

Image processing has been a challenging and multidisciplinary research area since decades with continuing improvements in its various branches especially Medical Imaging. The healthcare industry was very much benefited with the advances in Image Processing techniques for the efficient management of large volumes of clinical data. The popularity and growth of Image Processing field attracts researchers from many disciplines including Computer Science and Medical Science due to its applicability to the real world. In the meantime, Computer Science is becoming an important driving force for the further development of Medical Sciences. The objective of this study is to make use of the basic concepts in Medical Image Processing and develop methods and tools for clinicians’ assistance. This work is motivated from clinical applications of digital mammograms and placental sonograms, and uses real medical images for proposing a method intended to assist radiologists in the diagnostic process. The study consists of two domains of Pattern recognition, Classification and Content Based Retrieval. Mammogram images of breast cancer patients and placental images are used for this study. Cancer is a disaster to human race. The accuracy in characterizing images using simplified user friendly Computer Aided Diagnosis techniques helps radiologists in detecting cancers at an early stage. Breast cancer which accounts for the major cause of cancer death in women can be fully cured if detected at an early stage. Studies relating to placental characteristics and abnormalities are important in foetal monitoring. The diagnostic variability in sonographic examination of placenta can be overlooked by detailed placental texture analysis by focusing on placental grading. The work aims on early breast cancer detection and placental maturity analysis. This dissertation is a stepping stone in combing various application domains of healthcare and technology.

A Comparative Study of Wavelet Based Feature Extraction Techniques in Recognizing Isolated Spoken Words

Speech is a natural mode of communication for people and speech recognition is an intensive area of research due to its versatile applications. This paper presents a comparative study of various feature extraction methods based on wavelets for recognizing isolated spoken words. Isolated words from Malayalam, one of the four major Dravidian languages of southern India are chosen for recognition. This work includes two speech recognition methods. First one is a hybrid approach with Discrete Wavelet Transforms and Artificial Neural Networks and the second method uses a combination of Wavelet Packet Decomposition and Artificial Neural Networks. Features are extracted by using Discrete Wavelet Transforms (DWT) and Wavelet Packet Decomposition (WPD). Training, testing and pattern recognition are performed using Artificial Neural Networks (ANN). The proposed method is implemented for 50 speakers uttering 20 isolated words each. The experimental results obtained show the efficiency of these techniques in recognizing speech