Nesta dissertação, foi utilizada a técnica SIFT (Scale Invariant Feature Transform) para o reconhecimento de imagens da área dos olhos (região periorbital). Foi implementada uma classificação das imagens em subgrupos internos ao banco de dados, utilizando-se das informações estatísticas provenientes dos padrões invariantes produzidos pela técnica SIFT. Procedeu-se a uma busca categorizada pelo banco de dados, ao invés da procura de um determinado padrão apresentado, através da comparação deste com cada padrão presente no banco de dados. A tais padrões foi aplicada uma abordagem estatística, através da geração da matriz de covariâncias dos padrões gerados, sendo esta utilizada para a categorização, tendo por base uma rede neural híbrida. A rede neural classifica e categoriza o banco de dados de imagens, criando uma topologia de busca. Foram obtidos resultados corretos de classificação de 76,3% pela rede neural híbrida, sendo que um algoritmo auxiliar determina uma hierarquia de busca, onde, ocorrendo uma errônea classificação, a busca segue em grupos de pesquisas mais prováveis.

A combinação de fontes biométricas não redundantes da multibiometria supera a precisão de cada fonte individual (monobiometria). Além do mais, dois problemas em biometria, ruído e ataques de usurpadores, podem ser minimizados pelo uso de múltiplos sensores e biometria multimodal. Entretanto, se as similaridades estão em todos traços biométricos, como em gêmeos monozigotos (MZ), o processamento de múltiplas fontes não melhora a performance. Para distinguir extrema similitude, influências epigenéticas e ambientais são mais importantes do que o DNA herdado. Esta tese examina a plasticidade fenotípica na assimetria humana como uma ferramenta para melhorar a multibiometria. A técnica de Processamento Bilateral (PB) é introduzida para analisar discordâncias em lados esquerdo e direito dos traços biométricos. PB foi testado com imagens de espectro visível e infravermelho usando Correlação Cruzada, Wavelets e Redes Neurais Artificiais. Os traços selecionados foram dentes, orelhas, íris, impressões digitais, narinas e bochechas. PB acústico também foi implementado para avaliação da assimetria vibracional durante sons vocálicos e comparado a um sistema reconhecedor de locutores com parametrização via MFCC (Mel Frequency Cepstral Coefficients) e classificado por Quantização Vetorial. Para o PB de imagens e acústico foram coletadas 20 amostras por traço biométrico durante um ano de nove irmãos masculinos adultos. Com propósito de teste, as biometrias esquerdas foram impostoras às biometrias direitas do mesmo indivíduo e vice-versa, o que levou a 18 entidades serem identificadas por traço biométrico. Resultados alcançaram identificação total em todas biometrias tratadas com PB, comparado a um máximo de 44% de identificação correta sem PB. Esta tese conclui que peculiaridades bilaterais melhoram a performance multibiométrica e podem complementar qualquer abordagem de reconhecimento. / Combination of non-redundant biometric sources in multibiometrics overcomes individual source accuracy (monobiometrics). Moreover, two problems in biometrics, noise and impostor attacks, can be minimized by the use of multi-sensor, multi-modal biometrics. However, if similarities are in all traits, as in monozygotic twins (MZ), multiple source processing does not improve performance. To distinguish extreme similitude, epigenetic and environmental influences are more important than DNA inherited. This thesis examines phenotypic plasticity in human asymmetry as a tool to ameliorate multibiometrics. Bilateral Processing (BP) technique is introduced to analyze discordances in left and right trait sides. BP was tested in visible and infrared spectrum images using Cross-Correlation, Wavelets and Artificial Neural Networks. Selected traits were teeth, ears, irises, fingerprints, nostrils and cheeks. Acoustic BP was also implemented for vibration asymmetry evaluation during voiced sounds and compared to a speaker recognition system parameterized via MFCC (Mel Frequency Cepstral Coefficients) and classified by Vector Quantization. Image and acoustic BP gathered 20 samples per biometric trait during one year from nine adult male brothers. For test purposes, left biometrics was impostor to right biometrics from the same individual and vice-versa, which led to 18 entities to be identified per trait. Results achieved total identification in all biometrics treated with BP, compared to maximum 44% of correct identification without BP. This study concludes that bilateral peculiarities improve multibiometric performance and can complement any recognition approach.

Dans son contexte spécifique, le terme « biométrie » est souvent associé à l'étude des caractéristiques physiques et comportementales des individus afin de parvenir à leur identification ou à leur vérification. Ainsi, le travail développé dans cette thèse nous a conduit à proposer un algorithme d'identification robuste, en considérant les caractéristiques intrinsèques des phalanges de la main. Considérée comme une biométrie cachée, cette nouvelle approche peut s'avérer intéressante, notamment lorsqu'il est question d'assurer un niveau de sécurité élevé, robuste aux différentes attaques qu'un système biométrique doit contrer. La base des techniques proposées requière trois phases, à savoir: (1) la segmentation des phalanges, (2) l'extraction de leurs caractéristiques par la génération d'une empreinte, appelée « Phalange-Code » et (3) l'identification basée sur la méthode du 1-plus proche voisin ou la vérification basée sur une métrique de similarité. Ces algorithmes opèrent sur des niveaux hiérarchiques permettant l'extraction de certains paramètres, invariants à des transformations géométriques telles que l'orientation et la translation. De plus, nous avons considéré des techniques robustes au bruit, pouvant opérer à différentes résolutions d'images. Plus précisément, nous avons élaboré trois approches de reconnaissance biométrique : la première approche utilise l'information spectrale des contours des phalanges de la main comme signature individuelle, alors que la deuxième approche nécessite l'utilisation des caractéristiques géométriques et morphologiques des phalanges (i.e. surface, périmètre, longueur, largeur, capacité). Enfin, la troisième approche requière la génération d'un nouveau rapport de vraisemblance entre les phalanges, utilisant la théorie de probabilités géométriques. En second lieu, la construction d'une base de données avec la plus faible dose de rayonnement a été l'un des grands défis de notre étude. Nous avons donc procédé par la collecte de 403 images radiographiques de la main, acquises en utilisant la machine Apollo EZ X-Ray. Ces images sont issues de 115 adultes volontaires (hommes et femmes), non pathologiques. L'âge moyen étant de 27.2 ans et l'écart-type est de 8.5. La base de données ainsi construite intègre des images de la main droite et gauche, acquises à des positions différentes et en considérant des résolutions différentes et des doses de rayonnement différentes (i.e. réduction jusqu'à 98 % de la dose standard recommandée par les radiologues « 1 µSv »).Nos expériences montrent que les individus peuvent être distingués par les caractéristiques de leurs phalanges, que ce soit celles de la main droite ou celles de la main gauche. Cette distinction est également valable pour le genre des individus (homme/femme). L'étude menée a montré que l'approche utilisant l'information spectrale des contours des phalanges permet une identification par seulement trois phalanges, à un taux EER (Equal Error Rate) inférieur à 0.24 %. Par ailleurs, il a été constaté « de manière surprenante » que la technique fondée sur les rapports de vraisemblance entre les phalanges permet d'atteindre un taux d'identification de 100 % et un taux d'EER de 0.37 %, avec une seule phalange. Hormis l'aspect identification/authentification, notre étude s'est penchée sur l'optimisation de la dose de rayonnement permettant une identification saine des individus. Ainsi, il a été démontré qu'il était possible d'acquérir plus de 12500/an d'images radiographiques de la main, sans pour autant dépasser le seuil administratif de 0.25 mSv / In its specific context, the term "biometrics" is often associated with the study of the physical and behavioral of individual's characteristics to achieve their identification or verification. Thus, the work developed in this thesis has led us to suggest a robust identification algorithm, taking into account the intrinsic characteristics of the hand phalanges. Considered as hidden biometrics, this new approach can be of high interest, particularly when it comes to ensure a high level of security, robust to various attacks that a biometric system must address. The basis of the proposed techniques requires three phases, namely: (1) the segmentation of the phalanges (2) extracting their characteristics by generating an imprint, called "Phalange-Code" and (3) the identification based on the method of 1-nearest neighbor or the verification based on a similarity metric. This algorithm operates on hierarchical levels allowing the extraction of certain parameters invariant to geometric transformations such as image orientation and translation. Furthermore, the considered algorithm is particularly robust to noise, and can function at different resolutions of images. Thus, we developed three approaches to biometric recognition: the first approach produces individual signature from the spectral information of the contours issued from the hand phalanges, whereas the second approach requires the use of geometric and morphological characteristics of the phalanges (i.e. surface, perimeter, length, width, and capacity). Finally, the third approach requires the generation of a new likelihood ratio between the phalanges, using the geometric probability theory. Furthermore, the construction of a database with the lowest radiation dose was one of the great challenges of our study. We therefore proceeded with the collection of 403 x-ray images of the hand, acquired using the Apollo EZ X-Ray machine. These images are from 115 non-pathological volunteering adult (men and women). The average age is 27.2 years and the standard deviation is 8.5. Thus, the constructed database incorporates images of the right and left hands, acquired at different positions and by considering different resolutions and different radiation doses (i.e. reduced till 98% of the standard dose recommended by radiologists "1 µSv").Our experiments show that individuals can be distinguished by the characteristics of their phalanges, whether those of the right hand or the left hand. This distinction also applies to the kind of individuals (male/female). The study has demonstrated that the approach using the spectral information of the phalanges' contours allows identification by only three phalanges, with an EER (Equal Error Rate) lower than 0.24 %. Furthermore, it was found “Surprisingly” that the technique based on the likelihood ratio between phalanges reaches an identification rate of 100% and an EER of 0.37% with a single phalanx. Apart from the identification/authentication aspect, our study focused on the optimization of the radiation dose in order to offer safe identification of individuals. Thus, it has been shown that it was possible to acquire more than 12,500/year radiographic hand images, without exceeding the administrative control of 0.25 mSv

The complexity of the interface between the muscular system and the nervous system is still elusive. We investigated how the neuromuscular system functions and how it is influenced by various perturbations. Postural stability was selected as the model system, because this system provides complex output, which could indicate underlying mechanisms and feedback loops of the neuromuscular system. We hypothesized that aging, physical pain, and mental and physical perturbations affect balancing strategy, and based on these observations, we constructed a model that simulates many aspects of the neuromuscular system. Our results show that aging changes the control strategy of balancing from more chaotic to more repetitive. The chaotic elements ensure quick reactions and strong capacity to compensate for the perturbations; this adeptly reactive state changes into a less reactive, slower, probably less mechanically costly balancing strategy. Mental tasks during balancing also decreased the chaotic elements in balancing strategy, especially if the subject experienced chronic pain. Additional motoric tasks, such as tying knots while balancing, were correlated with age but unaffected by chronic pain. Our model competently predicted the experimental findings, and we proceeded to use the model with an external data set from Physionet to predict the balancing strategy of Parkinson’s patients. Our neurological model, comprised of RLC circuits, provides a mechanistic explanation for the neuromuscular system adaptations.

Literature has identified the need to study socially pervasive ICT in context in order to understand how user acceptability of innovation varies according to different inputs. This thesis contributes to the existing body of knowledge on innovation studies (Chapter 2) and proposes a methodology for a conceptual model, for representing dynamic contextual changes in longitudinal studies. The foundation for this methodology is the 'Price of Convenience' (PoC) Model (Chapter 4). As a theory development Thesis, it deals with two related studies of socially pervasive ICT implementation: (1) voluntary adoption of innovations and (2) acceptance of new socially pervasive and ubiquitous ICT innovations (Chapters 6 and 7).

Dans cette thèse nous nous concentrons sur une caractéristique locale du visage humain que sont les lèvres en termes de pertinence et influence sur la reconnaissance de la personne. Une étude détaillée est réalisée à l'égard de différentes étapes, telles que la détection, l'évaluation, la normalisation et les applications liées de la bouche. Au départ, on présente un algorithme de détection des lèvres en fusionnant deux méthodes indépendantes. La première méthode est basée sur la détection de contours et la deuxième orientée sur la segmentation. On exploite leurs points forts en combinant les deux méthodes par fusion. Ensuite, on extrait les caractéristiques qui modélisent l'aspect comportemental du mouvement des lèvres lorsque la personne parle afin de les exploiter pour la reconnaissance des personnes. Les caractéristiques du comportement incluent des caractéristiques statiques, et des caractéristiques dynamiques en fonction du flux optique. Ces caractéristiques sont utilisées pour construire le modèle du client par une Mixture de Gaussiennes et enfin la classification est réalisée en utilisant une règle de décision bayésienne. Enfin, on propose une méthode de normalisation temporelle pour le traitement des variations du mouvement des lèvres pendant le discours. Étant donné plusieurs vidéos où une personne répète la même phrase plusieurs fois, nous étudions le mouvement des lèvres dans l'une de ces vidéos et on sélectionne certaines images clés comme images de synchronisation. Après, on synchronise le reste des vidéos par rapport au images clés de la première vidéo. Enfin toutes les vidéos sont normalisées temporellement par interpolation à l'aide de "morphing".

<p>Biometrics deals with identifying individuals with help of their biological data. Fingerprint scanning is the most common method of the biometric methods available today. The security of fingerprint scanners has however been questioned and previous studies have shown that fingerprint scanners can be fooled with artificial fingerprints, i.e. copies of real fingerprints. The fingerprint recognition systems are evolving and this study will discuss the situation of today. </p><p>Two approaches have been used to find out how good fingerprint recognition systems are in distinguishing between live fingers and artificial clones. The first approach is a literature study, while the second consists of experiments. </p><p>A literature study of liveness detection in fingerprint recognition systems has been performed. A description of different liveness detection methods is presented and discussed. Methods requiring extra hardware use temperature, pulse, blood pressure, electric resistance, etc., and methods using already existent information in the system use skin deformation, pores, perspiration, etc. </p><p>The experiments focus on making artificial fingerprints in gelatin from a latent fingerprint. Nine different systems were tested at the CeBIT trade fair in Germany and all were deceived. Three other different systems were put up against more extensive tests with three different subjects. All systems werecircumvented with all subjects'artificial fingerprints, but with varying results. The results are analyzed and discussed, partly with help of the A/R value defined in this report.</p>

<p>Different security issues are a top subject around the world, especially since the terror threats seem to intensify. In the same time, the transport industry suffer from problems with smuggling and theft of valuable goods. One way to increase the security might be to have a verification system installed in commercial trucks, in order to assure that the driver is the proper one.</p><p>This thesis has two purposes. One is to find appropriate methods for driver verification and build a prototype of a verification system which can be used for testing and further development. The other is to study how truck drivers perceive such a system and how their conception goes along with the growing demand for higher security. The present work is the result of a cooperation between an engineer and a cognitive scientist. The thesis focuses on the transport industry and was performed for Volvo Technology Corporation (VTEC), Gothenburg, Sweden.</p><p>Eleven available verification methods were studied. To enable a well-based selection of methods to implement in the prototype, inquiries and interviews with truck drivers and haulage contractors were carried out to complement the theoretical study.</p><p>One regular and three biometric verification methods were chosen for the test; fingerprint verification, face recognition, voice recognition and PIN verification. These methods were put together to a prototype system that was implemented in a truck simulator. A graphical user interface was developed in order to make the system user friendly. The prototype system was tested by 18 truck drivers. They were thoroughly interviewed before and after the test in order to retrieve their background, expectations and opinions as well as their perceptions and experiences of the test.</p><p>Most of the test participants were positive to the prototype system. Even though they did not feel a need for it today they believed it to “be the future”. However, some participants felt uncomfortable with the system since they felt controlled by it. It became clear how important it is to have a system that respect the users’ privacy and to assure that the users are well informed about how the system is used. Some of the technology used for the verification system requires more development to fit in the automotive context, but it is considered to be possible to achieve a secure and robust system.</p>

This dissertation describes a new methodology for multi-modal (2-D + 3-D) face modeling and recognition. There are advantages in using each modality for face recognition. For example, the problems of pose variation and illumination condition, which cannot be resolved easily by using the 2-D data, can be handled by using the 3-D data. However, texture, which is provided by 2-D data, is an important cue that cannot be ignored. Therefore, we use both the 2-D and 3-D modalities for face recognition and fuse the results of face recognition by each modality to boost the overall performance of the system. In this dissertation, we consider two different cases for multi-modal face modeling and recognition. In the first case, the 2-D and 3-D data are registered. In this case we develop a unified graph model called Attributed Relational Graph (ARG) for face modeling and recognition. Based on the ARG model, the 2-D and 3-D data are included in a single model. The developed ARG model consists of nodes, edges, and mutual relations. The nodes of the graph correspond to the landmark points that are extracted by an improved Active Shape Model (ASM) technique. In order to extract the facial landmarks robustly, we improve the Active Shape Model technique by using the color information. Then, at each node of the graph, we calculate the response of a set of log-Gabor filters applied to the facial image texture and shape information (depth values); these features are used to model the local structure of the face at each node of the graph. The edges of the graph are defined based on Delaunay triangulation and a set of mutual relations between the sides of the triangles are defined. The mutual relations boost the final performance of the system. The results of face matching using the 2-D and 3-D attributes and the mutual relations are fused at the score level. In the second case, the 2-D and 3-D data are not registered. This lack of registration could be due to different reasons such as time lapse between the data acquisitions. Therefore, the 2-D and 3-D modalities are modeled independently. For the 3-D modality, we developed a fully automated system for 3-D face modeling and recognition based on ridge images. The problem with shape matching approaches such as Iterative Closest Points (ICP) or Hausdorff distance is the computational complexity. We model the face by 3-D binary ridge images and use them for matching. In order to match the ridge points (either using the ICP or the Hausdorff distance), we extract three facial landmark points: namely, the two inner corners of the eyes and the tip of the nose, on the face surface using the Gaussian curvature. These three points are used for initial alignment of the constructed ridge images. As a result of using ridge points, which are just a fraction of the total points on the surface of the face, the computational complexity of the matching is reduced by two orders of magnitude. For the 2-D modality, we model the face using an Attributed Relational Graph. The results of the 2-D and 3-D matching are fused at the score level. There are various techniques to fuse the 2-D and 3-D modalities. In this dissertation, we fuse the matching results at the score level to enhance the overall performance of our face recognition system. We compare the Dempster-Shafer theory of evidence and the weighted sum rule for fusion. We evaluate the performance of the above techniques for multi-modal face recognition on various databases such as Gavab range database, FRGC (Face Recognition Grand Challenge) V2.0, and the University of Miami face database.

Speaker verification is the biometric task of authenticating a claimed identity by means of analyzing a spoken sample of the claimant's voice. The present thesis deals with various topics related to automatic speaker verification (ASV) in the context of its commercial applications, characterized by co-operative users, user-friendly interfaces, and requirements for small amounts of enrollment and test data. A text-dependent system based on hidden Markov models (HMM) was developed and used to conduct experiments, including a comparison between visual and aural strategies for prompting claimants for randomized digit strings. It was found that aural prompts lead to more errors in spoken responses and that visually prompted utterances performed marginally better in ASV, given that enrollment data were visually prompted. High-resolution flooring techniques were proposed for variance estimation in the HMMs, but results showed no improvement over the standard method of using target-independent variances copied from a background model. These experiments were performed on Gandalf, a Swedish speaker verification telephone corpus with 86 client speakers. A complete on-site application (PER), a physical access control system securing a gate in a reverberant stairway, was implemented based on a combination of the HMM and a Gaussian mixture model based system. Users were authenticated by saying their proper name and a visually prompted, random sequence of digits after having enrolled by speaking ten utterances of the same type. An evaluation was conducted with 54 out of 56 clients who succeeded to enroll. Semi-dedicated impostor attempts were also collected. An equal error rate (EER) of 2.4% was found for this system based on a single attempt per session and after retraining the system on PER-specific development data. On parallel telephone data collected using a telephone version of PER, 3.5% EER was found with landline and around 5% with mobile telephones. Impostor attempts in this case were same-handset attempts. Results also indicate that the distribution of false reject and false accept rates over target speakers are well described by beta distributions. A state-of-the-art commercial system was also tested on PER data with similar performance as the baseline research system. / QC 20100910