**Êtes-vous un étudiant de l'EPFL à la recherche d'un projet de semestre?**

Travaillez avec nous sur des projets en science des données et en visualisation, et déployez votre projet sous forme d'application sur GraphSearch.

Concept# Biométrie

Résumé

Le mot biométrie signifie littéralement « mesure du vivant » et désigne dans un sens très large l'étude quantitative des êtres vivants. Parmi les principaux domaines d'application de la biométrie, on peut citer l'agronomie, l'anthropologie, l'écologie et la médecine.
L'usage de ce terme se rapporte de plus en plus à l'usage de ces techniques à des fins de reconnaissance, d'authentification et d'identification, le sens premier du mot biométrie étant alors repris par le terme biostatistique.
La biométrie est la vérification de l'identité d'un individu par ce qu'il est, c'est-à-dire en utilisant des caractéristiques physiques ou comportementales.
Différentes significations
Étude quantitative des êtres vivants
Durant tout le , le mot « biométrie » a été utilisé quasi exclusivement dans le sens très large de l'« étude quantitative des êtres vivants », notamment à l'aide des méthodes statistiques. C'est dans cette optique que la revue Biometrika paraît depuis 1901 et

Source officielle

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées

Chargement

Personnes associées

Chargement

Unités associées

Chargement

Concepts associés

Chargement

Cours associés

Chargement

Séances de cours associées

Chargement

Personnes associées (15)

Concepts associés (25)

Empreinte digitale

vignette| upright=0.9| Photo d'une empreinte digitale.
vignette| upright=0.8| Dermatoglyphes d'un doigt : plis papillaires (crêtes et sillons).
Une empreinte digitale ou dactylogramme est le dessin

Authentification

thumb|Authentification renforcée basée sur une cryptocard
L'authentification est un processus permettant à un système informatique de s'assurer de la légitimité de la demande d'accès faite par une en

Système de reconnaissance faciale

Un système de reconnaissance faciale est une application logicielle visant à reconnaître automatiquement une personne grâce à son visage. Il s'agit d'un sujet particulièrement étudié en vision par ord

Cours associés (12)

COM-301: Computer security

This is an introductory course to computer security and privacy. Its goal is to provide students with means to reason about security and privacy problems, and provide them with tools to confront them.

CS-438: Decentralized systems engineering

A decentralized system is one that works when no single party is in charge or fully trusted. This course teaches decentralized systems principles while guiding students through the development and testing of their own decentralized system incorporating messaging, encryption, and blockchain concepts.

COM-402: Information security and privacy

This course provides an overview of information security and privacy topics. It introduces students to the knowledge and tools they will need to deal with the security/privacy challenges they are likely to encounter in today's Big Data world. The tools are illustrated with relevant applications.

Publications associées (100)

Chargement

Chargement

Chargement

Unités associées (5)

Séances de cours associées (17)

Verifying a person's identity claim by combining multiple biometric systems (fusion) is a promising solution to identity theft and automatic access control. This thesis contributes to the state-of-the-art of multimodal biometric fusion by improving the understanding of fusion and by enhancing fusion performance using information specific to a user. One problem to deal with at the score level fusion is to combine system outputs of different types. Two statistically sound representations of scores are probability and log-likelihood ratio (LLR). While they are equivalent in theory, LLR is much more useful in practice because its distribution can be approximated by a Gaussian distribution, which makes it useful to analyze the problem of fusion. Furthermore, its score statistics (mean and covariance) conditioned on the claimed user identity can be better exploited. Our first contribution is to estimate the fusion performance given the class-conditional score statistics and given a particular fusion operator/classifier. Thanks to the score statistics, we can predict fusion performance with reasonable accuracy, identify conditions which favor a particular fusion operator, study the joint phenomenon of combining system outputs with different degrees of strength and correlation and possibly correct the adverse effect of bias (due to the score-level mismatch between training and test sets) on fusion. While in practice the class-conditional Gaussian assumption is not always true, the estimated performance is found to be acceptable. Our second contribution is to exploit the user-specific prior knowledge by limiting the class-conditional Gaussian assumption to each user. We exploit this hypothesis in two strategies. In the first strategy, we combine a user-specific fusion classifier with a user-independent fusion classifier by means of two LLR scores, which are then weighted to obtain a single output. We show that combining both user-specific and user-independent LLR outputs always results in improved performance than using the better of the two. In the second strategy, we propose a statistic called the user-specific F-ratio, which measures the discriminative power of a given user based on the Gaussian assumption. Although similar class separability measures exist, e.g., the Fisher-ratio for a two-class problem and the d-prime statistic, F-ratio is more suitable because it is related to Equal Error Rate in a closed form. F-ratio is used in the following applications: a user-specific score normalization procedure, a user-specific criterion to rank users and a user-specific fusion operator that selectively considers a subset of systems for fusion. The resultant fusion operator leads to a statistically significantly increased performance with respect to the state-of-the-art fusion approaches. Even though the applications are different, the proposed methods share the following common advantages. Firstly, they are robust to deviation from the Gaussian assumption. Secondly, they are robust to few training data samples thanks to Bayesian adaptation. Finally, they consider both the client and impostor information simultaneously.

Verifying a person's identity claim by combining multiple biometric systems (fusion) is a promising solution to identity theft and automatic access control. This thesis contributes to the state-of-the-art of multimodal biometric fusion by improving the understanding of fusion and by enhancing fusion performance using information specific to a user. One problem to deal with at the score level fusion is to combine system outputs of different types. Two statistically sound representations of scores are probability and log-likelihood ratio (LLR). While they are equivalent in theory, LLR is much more useful in practice because its distribution can be approximated by a Gaussian distribution, which makes it useful to analyze the problem of fusion. Furthermore, its score statistics (mean and covariance) conditioned on the claimed user identity can be better exploited. Our first contribution is to estimate the fusion performance given the class-conditional score statistics and given a particular fusion operator/classifier. Thanks to the score statistics, we can predict fusion performance with reasonable accuracy, identify conditions which favor a particular fusion operator, study the joint phenomenon of combining system outputs with different degrees of strength and correlation and possibly correct the adverse effect of bias (due to the score-level mismatch between training and test sets) on fusion. While in practice the class-conditional Gaussian assumption is not always true, the estimated performance is found to be acceptable. Our second contribution is to exploit the user-specific prior knowledge by limiting the class-conditional Gaussian assumption to each user. We exploit this hypothesis in two strategies. In the first strategy, we combine a user-specific fusion classifier with a user-independent fusion classifier by means of two LLR scores, which are then weighted to obtain a single output. We show that combining both user-specific and user-independent LLR outputs always results in improved performance than using the better of the two. In the second strategy, we propose a statistic called the user-specific F-ratio, which measures the discriminative power of a given user based on the Gaussian assumption. Although similar class separability measures exist, e.g., the Fisher-ratio for a two-class problem and the d-prime statistic, F-ratio is more suitable because it is related to Equal Error Rate in a closed form. F-ratio is used in the following applications: a user-specific score normalization procedure, a user-specific criterion to rank users and a user-specific fusion operator that selectively considers a subset of systems for fusion. The resultant fusion operator leads to a statistically significantly increased performance with respect to the state-of-the-art fusion approaches. Even though the applications are different, the proposed methods share the following common advantages. Firstly, they are robust to deviation from the Gaussian assumption. Secondly, they are robust to few training data samples thanks to Bayesian adaptation. Finally, they consider both the client and impostor information simultaneously.

Since the beginning of this brand new century, and especially since the 2001 Sept 11 events in the U.S, several biometric technologies are considered mature enough to be a new tool for security. Generally associated to a personal device for privacy protection, biometric references are stored in secured electronic devices such as smart cards, and systems are using cryptographic tools to communicate with the smart card and securely exchange biometric data. After a general introduction about biometrics, smart cards and cryptography, a second part will introduce our work with fake finger attacks on fingerprint sensors and tests done with different materials. The third part will present our approach for a lightweight fingerprint recognition algorithm for smart cards. The fourth part will detail security protocols used in different applications such as Personal Identity Verification cards. We will discuss our implementation such as the one we developed for the NIST to be used in PIV smart cards. Finally, a fifth part will address Cryptography-Biometrics interaction. We will highlight the antagonism between Cryptography – determinism, stable data – and Biometrics – statistical, error-prone –. Then we will present our application of challenge-response protocol to biometric data for easing the fingerprint recognition process.