A Scalable Formulation of Probabilistic Linear Discriminant Analysis: Applied to Face Recognition

Shafey, Laurent El; McCool, Chris; Wallace, Roy; Marcel, Sébastien

doi:10.1109/tpami.2013.38

Cited by 63 publications

(52 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All the FR systems studied here have been tested within the same software framework. 5 Website: www.idiap.ch/software/bob/…”

Section: A Methodologymentioning

confidence: 99%

“…The first generation of large scale appearance based FR systems, such as Eigenfaces [1] and Fisherfaces [2], attempted to model the face-variability in a simple linear sub-space. Subsequently, methods such as joint factor analysis (JFA), inter-session variability (ISV) modeling [3] and probabilistic linear discriminant analysis (PLDA) [4,5] were developed to better model variability in face-images. Deep-learning based methods, notably convolutional neural networks (CNN) [6,7,8,9], have become very popular in recent years, due to their near-perfect recognition accuracy on unconstrained datasets such as 'labeled faces in the wild' (LFW) [10].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deeply vulnerable: a study of the robustness of face recognition to presentation attacks

2017

View full text Add to dashboard Cite

The vulnerability of deep-learning based face-recognition (FR) methods, to presentation attacks (PA) is studied in this paper. 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, maximizing recognition-performance alone is not sufficient -the system should also be capable of resisting various kinds of attacks, including presentation-attacks (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, we 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%.

show abstract

“…All the FR systems studied here have been tested within the same software framework. 5 Website: www.idiap.ch/software/bob/…”

Section: A Methodologymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deeply vulnerable: a study of the robustness of face recognition to presentation attacks

2017

View full text Add to dashboard Cite

show abstract

“…Performance of i-vector averaging and multi-session scoring is also studied in , whereas (Yaman and Pelecanos, 2013) includes a comparison of score-averaging and multi-session scoring. In the context of face recognition, a scalable formulation of PLDA is described in detail in (El Shafey et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

From single to multiple enrollment i-vectors: Practical PLDA scoring variants for speaker verification

Rajan

Afanasyev

Hautamäki

et al. 2014

Digital Signal Processing

View full text Add to dashboard Cite

The availability of multiple utterances (and hence, i-vectors) for speaker enrollment brings up several alternatives for their utilization with probabilistic linear discriminant analysis (PLDA). This paper provides an overview of their effective utilization, from a practical viewpoint. We derive expressions for the evaluation of the likelihood ratio for the multi-enrollment case, with details on the computation of the required matrix inversions and determinants. The performance of five different scoring methods, and the effect of i-vector length normalization is compared experimentally. We conclude that length normalization is a useful technique for all but one of the scoring methods considered, and averaging i-vectors is the most effective out of the methods compared. We also study the application of multicondition training on the PLDA model. Our experiments indicate that multicondition training is more effective in estimating PLDA hyperparameters than it is for likelihood computation. Finally, we look at the effect of the configuration of the enrollment data on PLDA scoring, studying the properties of conditional dependence and number-of-enrollment-utterances per target speaker. Our experiments indicate that these properties affect the performance of the PLDA model. These results further support the conclusion that i-vector averaging is a simple and effective way to process multiple enrollment utterances.

show abstract

“…In [14], the authors utilize a special matrix structure of PLDA model and manually derive equations for the required matrix inversions. In [15], the authors proposed a special change of variables that lead to a diagonalized versions of the required matrices. The most detailed derivations are given in [16].…”

Section: Em-algorithmsmentioning

confidence: 99%

Unifying Probabilistic Linear Discriminant Analysis Variants in Biometric Authentication

Сизов

Lee

Kinnunen

2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Probabilistic linear discriminant analysis (PLDA) is commonly used in biometric authentication. We review three PLDA variants -standard, simplified and two-covariance -and show how they are related. These clarifications are important because the variants were introduced in literature without argumenting their benefits. We analyse their predictive power, covariance structure and provide scalable algorithms for straightforward implementation of all the three variants. Experiments involve state-of-the-art speaker verification with i-vector features.

show abstract

A Scalable Formulation of Probabilistic Linear Discriminant Analysis: Applied to Face Recognition

Cited by 63 publications

References 13 publications

Deeply vulnerable: a study of the robustness of face recognition to presentation attacks

Deeply vulnerable: a study of the robustness of face recognition to presentation attacks

From single to multiple enrollment i-vectors: Practical PLDA scoring variants for speaker verification

Unifying Probabilistic Linear Discriminant Analysis Variants in Biometric Authentication

Contact Info

Product

Resources

About