Analyse de mouvements faciaux à partir d'images vidéo

Lors d'une intervention conversationnelle, le langage est supporté par une communication non-verbale qui joue un rôle central dans le comportement social humain en permettant de la rétroaction et en gérant la synchronisation, appuyant ainsi le contenu et la signification du discours. En effet, 55% du message est véhiculé par les expressions faciales, alors que seulement 7% est dû au message linguistique et 38% au paralangage. L'information concernant l'état émotionnel d'une personne est généralement inférée par les attributs faciaux. Cependant, on ne dispose pas vraiment d'instruments de mesure spécifiquement dédiés à ce type de comportements. En vision par ordinateur, on s'intéresse davantage au développement de systèmes d'analyse automatique des expressions faciales prototypiques pour les applications d'interaction homme-machine, d'analyse de vidéos de réunions, de sécurité, et même pour des applications cliniques. Dans la présente recherche, pour appréhender de tels indicateurs observables, nous essayons d'implanter un système capable de construire une source consistante et relativement exhaustive d'informations visuelles, lequel sera capable de distinguer sur un visage les traits et leurs déformations, permettant ainsi de reconnaître la présence ou absence d'une action faciale particulière. Une réflexion sur les techniques recensées nous a amené à explorer deux différentes approches. La première concerne l'aspect apparence dans lequel on se sert de l'orientation des gradients pour dégager une représentation dense des attributs faciaux. Hormis la représentation faciale, la principale difficulté d'un système, qui se veut être général, est la mise en œuvre d'un modèle générique indépendamment de l'identité de la personne, de la géométrie et de la taille des visages. La démarche qu'on propose repose sur l'élaboration d'un référentiel prototypique à partir d'un recalage par SIFT-flow dont on démontre, dans cette thèse, la supériorité par rapport à un alignement conventionnel utilisant la position des yeux. Dans une deuxième approche, on fait appel à un modèle géométrique à travers lequel les primitives faciales sont représentées par un filtrage de Gabor. Motivé par le fait que les expressions faciales sont non seulement ambigües et incohérentes d'une personne à une autre mais aussi dépendantes du contexte lui-même, à travers cette approche, on présente un système personnalisé de reconnaissance d'expressions faciales, dont la performance globale dépend directement de la performance du suivi d'un ensemble de points caractéristiques du visage. Ce suivi est effectué par une forme modifiée d'une technique d'estimation de disparité faisant intervenir la phase de Gabor. Dans cette thèse, on propose une redéfinition de la mesure de confiance et introduisons une procédure itérative et conditionnelle d'estimation du déplacement qui offrent un suivi plus robuste que les méthodes originales.

Mouvement biologique et entraînement perceptivo-cognitif chez les personnes âgées

Lorsque nous cherchons un ami dans une foule ou attendons un proche sur le quai d’une gare, l’identification de cette personne nous est souvent possible grâce à la reconnaissance de sa démarche. Plusieurs chercheurs se sont intéressés à la façon de se mouvoir de l’être humain en étudiant le mouvement biologique. Le mouvement biologique est la représentation, par un ensemble structuré de points lumineux animés, des gestes d’un individu en mouvement dans une situation particulière (marche, golf, tennis, etc.). Une des caractéristiques du patron de mouvement biologique peu étudiée et néanmoins essentielle est sa taille. La plupart des études concernées utilisent des patrons de petite taille correspondant à une personne située à 16 mètres de l’observateur. Or les distances d’interaction sociale, chez l’humain, sont généralement inférieures à 16 mètres. D’autre part, les résultats des études portant sur la perception des patrons de mouvement biologique et le vieillissement demeurent contradictoires. Nous avons donc, dans un premier temps, évalué, dans une voûte d’immersion en réalité virtuelle, l’importance de la distance entre l’observateur et le patron de mouvement biologique, chez des adultes jeunes et des personnes âgées. Cette étude a démontré que l’évaluation de la direction de mouvement d’un patron devient difficile pour les personnes âgées lorsque le patron est situé à moins de 4 mètres, alors que les résultats des jeunes sont comparables pour toutes distances, à partir d’un mètre et au-delà. Cela indique que les gens âgés peinent à intégrer l’information occupant une portion étendue de leur champ visuel, ce qui peut s’avérer problématique dans des espaces où les distances d’interaction sont inférieures à 4 mètres. Nombre de recherches indiquent aussi clairement que les gens âgés s’adaptent difficilement à des situations complexes. Nous avons donc cherché, dans un second temps, à minimiser ces altérations liées à l’âge de l’intégration des processus complexes, en utilisant une tâche adaptée à l’entraînement et à l’évaluation de l’intégration de ces processus : la poursuite multiple d’objets dans l’espace ou 3D-MOT (3 Dimensions Multiple Object Tracking). Le 3D-MOT consiste à suivre simultanément plusieurs objets d’intérêt en mouvement parmi des distracteurs également en mouvement. Nous avons évalué les habiletés de participants jeunes et âgés à une telle tâche dans un environnement virtuel en 3D en déterminant la vitesse maximale de déplacement des objets à laquelle la tâche pouvait être exécutée. Les résultats des participants âgés étaient initialement inférieurs à ceux des jeunes. Cependant, après plusieurs semaines d’entraînement, les personnes âgées ont obtenu des résultats comparables à ceux des sujets jeunes non entraînés. Nous avons enfin évalué, pour ces mêmes participants, l’impact de cet entraînement sur la perception de patrons de mouvement biologique présentés à 4 et 16 mètres dans l’espace virtuel : les habiletés des personnes âgées entraînées obtenues à 4 mètres ont augmenté de façon significative pour atteindre le niveau de celles obtenues à 16 mètres. Ces résultats suggèrent que l’entraînement à certaines tâches peut réduire les déclins cognitivo-perceptifs liés à l’âge et possiblement aider les personnes âgées dans leurs déplacements quotidiens.

Speech Analysis using Modern Techniques of Nonlinear Dynamics

Medical fields requires fast, simple and noninvasive methods of diagnostic techniques. Several methods are available and possible because of the growth of technology that provides the necessary means of collecting and processing signals. The present thesis details the work done in the field of voice signals. New methods of analysis have been developed to understand the complexity of voice signals, such as nonlinear dynamics aiming at the exploration of voice signals dynamic nature. The purpose of this thesis is to characterize complexities of pathological voice from healthy signals and to differentiate stuttering signals from healthy signals. Efficiency of various acoustic as well as non linear time series methods are analysed. Three groups of samples are used, one from healthy individuals, subjects with vocal pathologies and stuttering subjects. Individual vowels/ and a continuous speech data for the utterance of the sentence "iruvarum changatimaranu" the meaning in English is "Both are good friends" from Malayalam language are recorded using a microphone . The recorded audio are converted to digital signals and are subjected to analysis.Acoustic perturbation methods like fundamental frequency (FO), jitter, shimmer, Zero Crossing Rate(ZCR) were carried out and non linear measures like maximum lyapunov exponent(Lamda max), correlation dimension (D2), Kolmogorov exponent(K2), and a new measure of entropy viz., Permutation entropy (PE) are evaluated for all three groups of the subjects. Permutation Entropy is a nonlinear complexity measure which can efficiently distinguish regular and complex nature of any signal and extract information about the change in dynamics of the process by indicating sudden change in its value. The results shows that nonlinear dynamical methods seem to be a suitable technique for voice signal analysis, due to the chaotic component of the human voice. Permutation entropy is well suited due to its sensitivity to uncertainties, since the pathologies are characterized by an increase in the signal complexity and unpredictability. Pathological groups have higher entropy values compared to the normal group. The stuttering signals have lower entropy values compared to the normal signals.PE is effective in charaterising the level of improvement after two weeks of speech therapy in the case of stuttering subjects. PE is also effective in characterizing the dynamical difference between healthy and pathological subjects. This suggests that PE can improve and complement the recent voice analysis methods available for clinicians. The work establishes the application of the simple, inexpensive and fast algorithm of PE for diagnosis in vocal disorders and stuttering subjects.

Studies on the propagation of errors in physical oceanographic computations

The results of an investigation on the limits of the random errors contained in the basic data of Physical Oceanography and their propagation through the computational procedures are presented in this thesis. It also suggest a method which increases the reliability of the derived results. The thesis is presented in eight chapters including the introductory chapter. Chapter 2 discusses the general theory of errors that are relevant in the context of the propagation of errors in Physical Oceanographic computations. The error components contained in the independent oceanographic variables namely, temperature, salinity and depth are deliniated and quantified in chapter 3. Chapter 4 discusses and derives the magnitude of errors in the computation of the dependent oceanographic variables, density in situ, gt, specific volume and specific volume anomaly, due to the propagation of errors contained in the independent oceanographic variables. The errors propagated into the computed values of the derived quantities namely, dynamic depth and relative currents, have been estimated and presented chapter 5. Chapter 6 reviews the existing methods for the identification of level of no motion and suggests a method for the identification of a reliable zero reference level. Chapter 7 discusses the available methods for the extension of the zero reference level into shallow regions of the oceans and suggests a new method which is more reliable. A procedure of graphical smoothening of dynamic topographies between the error limits to provide more reliable results is also suggested in this chapter. Chapter 8 deals with the computation of the geostrophic current from these smoothened values of dynamic heights, with reference to the selected zero reference level. The summary and conclusion are also presented in this chapter.

Speech sample estimation from composite zerocrossings and encoding via adaptive switching of transforms

This thesis investigates the potential use of zerocrossing information for speech sample estimation. It provides 21 new method tn) estimate speech samples using composite zerocrossings. A simple linear interpolation technique is developed for this purpose. By using this method the A/D converter can be avoided in a speech coder. The newly proposed zerocrossing sampling theory is supported with results of computer simulations using real speech data. The thesis also presents two methods for voiced/ unvoiced classification. One of these methods is based on a distance measure which is a function of short time zerocrossing rate and short time energy of the signal. The other one is based on the attractor dimension and entropy of the signal. Among these two methods the first one is simple and reguires only very few computations compared to the other. This method is used imtea later chapter to design an enhanced Adaptive Transform Coder. The later part of the thesis addresses a few problems in Adaptive Transform Coding and presents an improved ATC. Transform coefficient with maximum amplitude is considered as ‘side information’. This. enables more accurate tfiiz assignment enui step—size computation. A new bit reassignment scheme is also introduced in this work. Finally, sum ATC which applies switching between luiscrete Cosine Transform and Discrete Walsh-Hadamard Transform for voiced and unvoiced speech segments respectively is presented. Simulation results are provided to show the improved performance of the coder

Development of a Biometric Personal Authentication System Based on Fingerprint and Speech

Biometrics deals with the physiological and behavioral characteristics of an individual to establish identity. Fingerprint based authentication is the most advanced biometric authentication technology. The minutiae based fingerprint identification method offer reasonable identification rate. The feature minutiae map consists of about 70-100 minutia points and matching accuracy is dropping down while the size of database is growing up. Hence it is inevitable to make the size of the fingerprint feature code to be as smaller as possible so that identification may be much easier. In this research, a novel global singularity based fingerprint representation is proposed. Fingerprint baseline, which is the line between distal and intermediate phalangeal joint line in the fingerprint, is taken as the reference line. A polygon is formed with the singularities and the fingerprint baseline. The feature vectors are the polygonal angle, sides, area, type and the ridge counts in between the singularities. 100% recognition rate is achieved in this method. The method is compared with the conventional minutiae based recognition method in terms of computation time, receiver operator characteristics (ROC) and the feature vector length. Speech is a behavioural biometric modality and can be used for identification of a speaker. In this work, MFCC of text dependant speeches are computed and clustered using k-means algorithm. A backpropagation based Artificial Neural Network is trained to identify the clustered speech code. The performance of the neural network classifier is compared with the VQ based Euclidean minimum classifier. Biometric systems that use a single modality are usually affected by problems like noisy sensor data, non-universality and/or lack of distinctiveness of the biometric trait, unacceptable error rates, and spoof attacks. Multifinger feature level fusion based fingerprint recognition is developed and the performances are measured in terms of the ROC curve. Score level fusion of fingerprint and speech based recognition system is done and 100% accuracy is achieved for a considerable range of matching threshold

Characterization of human and instrument related measurement errors

Measurement is the act or the result of a quantitative comparison between a given quantity and a quantity of the same kind chosen as a unit. It is generally agreed that all measurements contain errors. In a measuring system where both a measuring instrument and a human being taking the measurement using a preset process, the measurement error could be due to the instrument, the process or the human being involved. The first part of the study is devoted to understanding the human errors in measurement. For that, selected person related and selected work related factors that could affect measurement errors have been identified. Though these are well known, the exact extent of the error and the extent of effect of different factors on human errors in measurement are less reported. Characterization of human errors in measurement is done by conducting an experimental study using different subjects, where the factors were changed one at a time and the measurements made by them recorded. From the pre‐experiment survey research studies, it is observed that the respondents could not give the correct answers to questions related to the correct values [extent] of human related measurement errors. This confirmed the fears expressed regarding lack of knowledge about the extent of human related measurement errors among professionals associated with quality. But in postexperiment phase of survey study, it is observed that the answers regarding the extent of human related measurement errors has improved significantly since the answer choices were provided based on the experimental study. It is hoped that this work will help users of measurement in practice to better understand and manage the phenomena of human related errors in measurement.

Modified Block Adaptive Predictive Coder For Speech Processing

This thesis investigated the potential use of Linear Predictive Coding in speech communication applications. A Modified Block Adaptive Predictive Coder is developed, which reduces the computational burden and complexity without sacrificing the speech quality, as compared to the conventional adaptive predictive coding (APC) system. For this, changes in the evaluation methods have been evolved. This method is as different from the usual APC system in that the difference between the true and the predicted value is not transmitted. This allows the replacement of the high order predictor in the transmitter section of a predictive coding system, by a simple delay unit, which makes the transmitter quite simple. Also, the block length used in the processing of the speech signal is adjusted relative to the pitch period of the signal being processed rather than choosing a constant length as hitherto done by other researchers. The efficiency of the newly proposed coder has been supported with results of computer simulation using real speech data. Three methods for voiced/unvoiced/silent/transition classification have been presented. The first one is based on energy, zerocrossing rate and the periodicity of the waveform. The second method uses normalised correlation coefficient as the main parameter, while the third method utilizes a pitch-dependent correlation factor. The third algorithm which gives the minimum error probability has been chosen in a later chapter to design the modified coder The thesis also presents a comparazive study beh-cm the autocorrelation and the covariance methods used in the evaluaiicn of the predictor parameters. It has been proved that the azztocorrelation method is superior to the covariance method with respect to the filter stabf-it)‘ and also in an SNR sense, though the increase in gain is only small. The Modified Block Adaptive Coder applies a switching from pitch precitzion to spectrum prediction when the speech segment changes from a voiced or transition region to an unvoiced region. The experiments cont;-:ted in coding, transmission and simulation, used speech samples from .\£=_‘ajr2_1a:r1 and English phrases. Proposal for a speaker reecgnifion syste: and a phoneme identification system has also been outlized towards the end of the thesis.

COMBINED FEATURE EXTRACTION TECHNIQUES AND NAIVE BAYES CLASSIFIER FOR SPEECH RECOGNITION

Speech processing and consequent recognition are important areas of Digital Signal Processing since speech allows people to communicate more natu-rally and efficiently. In this work, a speech recognition system is developed for re-cognizing digits in Malayalam. For recognizing speech, features are to be ex-tracted from speech and hence feature extraction method plays an important role in speech recognition. Here, front end processing for extracting the features is per-formed using two wavelet based methods namely Discrete Wavelet Transforms (DWT) and Wavelet Packet Decomposition (WPD). Naive Bayes classifier is used for classification purpose. After classification using Naive Bayes classifier, DWT produced a recognition accuracy of 83.5% and WPD produced an accuracy of 80.7%. This paper is intended to devise a new feature extraction method which produces improvements in the recognition accuracy. So, a new method called Dis-crete Wavelet Packet Decomposition (DWPD) is introduced which utilizes the hy-brid features of both DWT and WPD. The performance of this new approach is evaluated and it produced an improved recognition accuracy of 86.2% along with Naive Bayes classifier.

PERFORMANCE OF DIFFERENT CLASSIFIERS IN SPEECH RECOGNITION

Speech is the most natural means of communication among human beings and speech processing and recognition are intensive areas of research for the last five decades. Since speech recognition is a pattern recognition problem, classification is an important part of any speech recognition system. In this work, a speech recognition system is developed for recognizing speaker independent spoken digits in Malayalam. Voice signals are sampled directly from the microphone. The proposed method is implemented for 1000 speakers uttering 10 digits each. Since the speech signals are affected by background noise, the signals are tuned by removing the noise from it using wavelet denoising method based on Soft Thresholding. Here, the features from the signals are extracted using Discrete Wavelet Transforms (DWT) because they are well suitable for processing non-stationary signals like speech. This is due to their multi- resolutional, multi-scale analysis characteristics. Speech recognition is a multiclass classification problem. So, the feature vector set obtained are classified using three classifiers namely, Artificial Neural Networks (ANN), Support Vector Machines (SVM) and Naive Bayes classifiers which are capable of handling multiclasses. During classification stage, the input feature vector data is trained using information relating to known patterns and then they are tested using the test data set. The performances of all these classifiers are evaluated based on recognition accuracy. All the three methods produced good recognition accuracy. DWT and ANN produced a recognition accuracy of 89%, SVM and DWT combination produced an accuracy of 86.6% and Naive Bayes and DWT combination produced an accuracy of 83.5%. ANN is found to be better among the three methods.

Analytical Study of Typographical Errors in OPACS and Corrective Measures

The present study is an attempt to highlight the problem of typographical errors in OPACS. The errors made while typing catalogue entries as well as importing bibliographical records from other libraries exist unnoticed by librarians resulting the non-retrieval of available records and affecting the quality of OPACs. This paper follows previous research on the topic mainly by Jeffrey Beall and Terry Ballard. The word “management” was chosen from the list of likely to be misspelled words identified by previous research. It was found that the word is wrongly entered in several forms in local, national and international OPACs justifying the observations of Ballard that typos occur in almost everywhere. Though there are lots of corrective measures proposed and are in use, the study asserts the fact that human effort is needed to get rid of the problem. The paper is also an invitation to the library professionals and system designers to construct a strategy to solve the issue

Speech Recognition of Malayalam Numbers

Digit speech recognition is important in many applications such as automatic data entry, PIN entry, voice dialing telephone, automated banking system, etc. This paper presents speaker independent speech recognition system for Malayalam digits. The system employs Mel frequency cepstrum coefficient (MFCC) as feature for signal processing and Hidden Markov model (HMM) for recognition. The system is trained with 21 male and female voices in the age group of 20 to 40 years and there was 98.5% word recognition accuracy (94.8% sentence recognition accuracy) on a test set of continuous digit recognition task.

Development & evaluation of different acoustic models for Malayalam continuous speech recognition

Performance of any continuous speech recognition system is dependent on the accuracy of its acoustic model. Hence, preparation of a robust and accurate acoustic model lead to satisfactory recognition performance for a speech recognizer. In acoustic modeling of phonetic unit, context information is of prime importance as the phonemes are found to vary according to the place of occurrence in a word. In this paper we compare and evaluate the effect of context dependent tied (CD tied) models, context dependent (CD) and context independent (CI) models in the perspective of continuous speech recognition of Malayalam language. The database for the speech recognition system has utterance from 21 speakers including 11 female and 10 males. Our evaluation results show that CD tied models outperforms CI models over 21%.

Connected digit speech recognition system for Malayalam language

A connected digit speech recognition is important in many applications such as automated banking system, catalogue-dialing, automatic data entry, automated banking system, etc. This paper presents an optimum speaker-independent connected digit recognizer forMalayalam language. The system employs Perceptual Linear Predictive (PLP) cepstral coefficient for speech parameterization and continuous density Hidden Markov Model (HMM) in the recognition process. Viterbi algorithm is used for decoding. The training data base has the utterance of 21 speakers from the age group of 20 to 40 years and the sound is recorded in the normal office environment where each speaker is asked to read 20 set of continuous digits. The system obtained an accuracy of 99.5 % with the unseen data.