A Comprehensive Experimental and Reproducible Study on Selfie Biometrics in Multistream and Heterogeneous Settings

This contribution presents a new database to address current challenges in face recognition. It contains face video sequences of 75 individuals acquired either through a laptop webcam or when mimicking the front-facing camera of a smartphone. Sequences have been acquired with a device allowing to record visual, near-infrared and depth data at the same time. Recordings have been made across three sessions with different, challenging illumination conditions and variations in pose. Together with the database, several experimental protocols are provided and correspond to real world scenarios, when a mismatch in conditions between enrollment and probe images occurs. A comprehensive set of baseline experiments using publicly available baseline algorithms show that extreme illumination conditions and pose variations are remaining issues. However, the usage of different data domains -and their fusion -allows to mitigate such variation. Finally, experiments on heterogeneous face recognition are also presented using a state-of-the-art model based on deep neural networks, and showed better performance. When applied to other tasks, this model proved to surpass all existing baselines as well. The data, as well as the code to reproduce all experiments are made publicly available to help foster research in selfie biometrics using latest imaging devices.

À propos de ce résultat

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.

Concepts associés

Chargement

Publications associées

Chargement

Tiago De Freitas Pereira, Guillaume Heusch, Sébastien Marcel
2019
Article

Résumé

Official source

https://infoscience.epfl.ch/record/270144?ln=fr

À propos de ce résultat

Concepts associés (18)

Concepts associés

Chargement

Publications associées (11)

Publications associées

Chargement

Continuously Reproducing Toolchains in Pattern Recognition and Machine Learning Experiments

André Anjos, Tiago De Freitas Pereira, Sébastien Marcel, Amir Mohammadi

Pattern recognition and machine learning research work often contains experimental results on real-world data, which corroborates hypotheses and provides a canvas for the development and comparison of new ideas. Results, in this context, are typically summarized as a set of tables and figures, allowing the comparison of various methods, highlighting the advantages of the proposed ideas. Unfortunately, result reproducibility is often an overlooked feature of original research publications, competitions, or benchmark evaluations. The main reason for such a gap is the complexity on the development of software associated with these reports. Software frameworks are difficult to install, maintain, and distribute, while scientific experiments often consist of many steps and parameters that are difficult to report. The increasingly rising complexity of research challenges make it even more difficult to reproduce experiments and results. In this paper, we emphasize that a reproducible research work should be repeatable, shareable, extensible, and stable, and discuss important lessons we learned in creating, distributing, and maintaining software and data for reproducible research in pattern recognition and machine learning. We focus on a specific use-case of face recognition and describe in details how we can make the recognition experiments reproducible in practice.

2017

Chargement

Deeply Vulnerable -- a study of the robustness of face recognition to presentation attacks

Sébastien Marcel, Amir Mohammadi

The vulnerability of deep-learning-based face-recognition (FR) methods, to presentation attacks (PA), is studied in this study. Recently, proposed FR methods based on deep neural networks (DNN) have been shown to outperform most other methods by a significant margin. In a trustworthy face-verification system, however, maximising recognition-performance alone is not sufficient – the system should also be capable of resisting various kinds of attacks, including PA. Previous experience has shown that the PA vulnerability of FR systems tends to increase with face-verification accuracy. Using several publicly available PA datasets, the authors show that DNN-based FR systems compensate for variability between bona fide and PA samples, and tend to score them similarly, which makes such FR systems extremely vulnerable to PAs. Experiments show the vulnerability of the studied DNN-based FR systems to be consistently higher than 90%, and often higher than 98%.

Inst Engineering Technology-Iet2017

Chargement

Exploiting foreign resources for DNN-based ASR

Philip Neil Garner, David Imseng, Petr Motlicek

Manual transcription of audio databases for the development of automatic speech recognition (ASR) systems is a costly and time-consuming process. In the context of deriving acoustic models adapted to a specific application, or in low-resource scenarios, it is therefore essential to explore alternatives capable of improving speech recognition results. In this paper, we investigate the relevance of foreign data characteristics, in particular domain and language, when using this data as an auxiliary data source for training ASR acoustic models based on deep neural networks (DNNs). The acoustic models are evaluated on a challenging bilingual database within the scope of the MediaParl project. Experimental results suggest that in-language (but out-of-domain) data is more beneficial than in-domain (but out-of-language) data when employed in either supervised or semi-supervised training of DNNs. The best performing ASR system, an HMM/GMM acoustic model that exploits DNN as a discriminatively trained feature extractor outperforms the best performing HMM/DNN hybrid by about 5 % relative (in terms of WER). An accumulated relative gain with respect to the MFCC-HMM/GMM baseline is about 30 % WER.

2015

Chargement

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

Méthode expérimentale

Les méthodes expérimentales scientifiques consistent à tester la validité d'une hypothèse, en reproduisant un phénomène (souvent en laboratoire) et en faisant varier un paramètre. Le paramètre que l

Reproductibilité

La reproductibilité d'une expérience scientifique est une des conditions qui permettent d'inclure les observations réalisées durant cette expérience dans le processus d'amélioration perpétuelle des