André Anjos's research while affiliated with Idiap Research Institute and other places

This paper introduces the resources necessary to develop and evaluate human assisted lifelong learning speaker diarization systems. It describes the ALLIES corpus and associated protocols, especially designed for diarization of a collection audio recordings across time. This dataset is compared to existing corpora and the performances of three baseline systems, based on x-vectors, i-vectors and VBxHMM, are reported for reference. Those systems are then extended to include an active correction process that efficiently guides a human annotator to improve the automatically generated hypotheses. An open-source simulated human expert is provided to ensure reproducibility of the human assisted correction process and its fair evaluation. An exhaustive evaluation, of the human assisted correction shows the high potential of this approach. The ALLIES corpus, a baseline system including the active correction module and all evaluation tools are made freely available to the scientific community.

Face recognition is a mainstream biometric authentication method. However, vulnerability to presentation attacks (a.k.a spoofing) limits its usability in unsupervised applications. Even though there are many methods available for tackling presentation attacks (PA), most of them fail to detect sophisticated attacks such as silicone masks. As the quality of presentation attack instruments improves over time, achieving reliable PA detection with visual spectra alone remains very challenging. We argue that analysis in multiple channels might help to address this issue. In this context, we propose a multi-channel Convolutional Neural Network based approach for presentation attack detection (PAD). We also introduce the new Wide Multi-Channel presentation Attack (WMCA) database for face PAD which contains a wide variety of 2D and 3D presentation attacks for both impersonation and obfuscation attacks. Data from different channels such as color, depth, near-infrared and thermal are available to advance the research in face PAD. The proposed method was compared with feature-based approaches and found to outperform the baselines achieving an ACER of 0.3% on the introduced dataset. The database and the software to reproduce the results are made available publicly.

Face recognition is a mainstream biometric authentication method. However, vulnerability to presentation attacks (a.k.a spoofing) limits its usability in unsupervised applications. Even though there are many methods available for tackling presentation attacks (PA), most of them fail to detect sophisticated attacks such as silicone masks. As the quality of presentation attack instruments improves over time, achieving reliable PA detection with visual spectra alone remains very challenging. We argue that analysis in multiple channels might help to address this issue. In this context, we propose a multi-channel Convolutional Neural Network based approach for presentation attack detection (PAD). We also introduce the new Wide Multi-Channel presentation Attack (WMCA) database for face PAD which contains a wide variety of 2D and 3D presentation attacks for both impersonation and obfuscation attacks. Data from different channels such as color, depth, near-infrared and thermal are available to advance the research in face PAD. The proposed method was compared with feature-based approaches and found to outperform the baselines achieving an ACER of 0.3% on the introduced dataset. The database and the software to reproduce the results are made available publicly.

The domain of presentation attacks (PAs), including vulnerability studies and detection (PAD), remains very much unexplored by available scientific literature in biometric vein recognition. Contrary to other modalities that use visual spectral sensors for capturing biometric samples, vein biometrics is typically implemented with near-infrared imaging. The use of invisible light spectra challenges the creation of instruments, but does not render it impossible. In this chapter, we provide an overview of current landscape for PA manufacturing in possible attack vectors for vein recognition, describe existing public databases and baseline techniques to counter such attacks. The reader will also find material to reproduce experiments and findings for finger vein recognition systems. We provide this material with the hope that it will be extended to other vein recognition systems and improved in time.

The undeniable convenience of face recognition (FR) based biometrics has made it an attractive tool for access control in various application areas, from airports to remote banking. Widespread adoption of face biometrics, however, depends on the perception of robustness of such systems. One particular vulnerability of FR systems comes from presentation attacks (PA), where a subject A attempts to impersonate another subject B, by presenting, say, a photograph of B to the biometric sensor (i.e., the camera). PAs are the most likely forms of attacks on face biometric systems, as the camera is the only component of the biometric system that is exposed to the outside world. Presentation attack detection (PAD) methods provide an additional layer of security to FR systems. The first edition of the Handbook of Biometric Anti-Spoofing included two chapters on face-PAD. In this chapter we review the significant advances in face-PAD research since the publication of the first edition of this book. In addition to new face-PAD methods designed for color images, we also discuss advances involving other imaging modalities, such as near-infrared (NIR) and thermal imaging. Research on detecting various kinds of attacks, both planar as well as involving three-dimensional masks, is reviewed. The chapter also summarizes a number of recently published datasets for face-PAD experiments.

Presentation attack detection (PAD, also known as anti-spoofing) systems, regardless of the technique, biometric mode or degree of independence of external equipment, are most commonly treated as binary classification systems. The two classes that they differentiate are bona-fide and presentation attack samples. From this perspective, their evaluation is equivalent to the established evaluation standards for the binary classification systems. However, PAD systems are designed to operate in conjunction with recognition systems and as such can affect their performance. From the point of view of a recognition system, the presentation attacks are a separate class that need to be detected and rejected. As the problem of presentation attack detection grows to this pseudo-ternary status, the evaluation methodologies for the recognition systems need to be revised and updated. Consequentially, the database requirements for presentation attack databases become more specific. The focus of this chapter is the task of biometric verification and its scope is three-fold: first, it gives the definition of the presentation attack detection problem from the two perspectives. Second, it states the database requirements for a fair and unbiased evaluation. Finally, it gives an overview of the existing evaluation techniques for presentation attacks detection systems and verification systems under presentation attacks.

The task of Heterogeneous Face Recognition consists in matching face images that are sensed in different domains, such as sketches to photographs (visual spectra images), thermal images to photographs or near-infrared images to photographs. In this work we suggest that high level features of Deep Convolutional Neural Networks trained on visual spectra images are potentially domain independent and can be used to encode faces sensed in different image domains. A generic framework for Heterogeneous Face Recognition is proposed by adapting Deep Convolutional Neural Networks low level features in, so called, “Domain Specific Units”. The adaptation using Domain Specific Units allow the learning of shallow feature detectors specific for each new image domain. Furthermore, it handles its transformation to a generic face space shared between all image domains. Experiments carried out with four different face databases covering three different image domains show substantial improvements, in terms of recognition rate, surpassing the state-of-the-art for most of them. This work is made reproducible: all the source code, scores and trained models of this approach are made publicly available.

Most of the research on vein biometrics addresses the problems of either palm or finger vein recognition with a considerably smaller emphasis on wrist vein modality. This paper paves the way to a better understanding of capabilities and challenges in the field of wrist vein verification. This is achieved by introducing and discussing a fully automatic cross-correlation based wrist vein verification technique. Overcoming the limitations of ordinary cross-correlation, the proposed system is capable of compensating for scale, translation and rotation between vein patterns in a computationally efficient way. Introduced comparison algorithm requires only two cross-correlation operations to compensate for both translation and rotation, moreover the well known property of log-polar transformation of Fourier magnitudes is not involved in any form. To emphasize the veins, a two-layer Hessian-based vein enhancement approach with adaptive brightness normalization is introduced, improving the connectivity and the stability of extracted vein patterns. The experiments on the publicly available PUT Vein wrist database give promising results with FNMR of 3.75% for FMR ≈ 0.1%. In addition we make this research reproducible providing the source code and instructions to replicate all findings in this work.

While face recognition systems got a significant boost in terms of recognition performance in recent years, they are known to be vulnerable to presentation attacks. Up to date, most of the research in the field of face anti-spoofing or presentation attack detection was considered as a two-class classification task: features of bona-fide samples versus features coming from spoofing attempts. The main focus has been on boosting the anti-spoofing performance for databases with identical types of attacks across both training and evaluation subsets. However, in realistic applications the types of attacks are likely to be unknown, potentially occupying a broad space in the feature domain. Therefore, a failure to generalize on unseen types of attacks is one of the main potential challenges in existing anti-spoofing approaches. First, to demonstrate the generalization issues of two-class anti-spoofing systems we establish new evaluation protocols for existing publicly available databases. Second, to unite the data collection efforts of various institutions we introduce a challenging Aggre-gated database composed of 3 publicly available datasets: Replay-Attack, Replay-Mobile and MSU MFSD, reporting the performance on it. Third, considering existing limitations we propose a number of systems approaching a task of presentation attack detection as an anomaly detection, or a one-class classification problem, using only bona-fide features in the training stage. Using less training data, hence requiring less effort in the data collection, the introduced approach demonstrates a better generalization properties against previously unseen types of attacks on the proposed Aggregated database.

This paper studies the problem of reproducible research in remote photoplethysmography (rPPG). Most of the work published in this domain is assessed on privately-owned databases, making it difficult to evaluate proposed algorithms in a standard and principled manner. As a consequence, we present a new, publicly available database containing a relatively large number of subjects recorded under two different lighting conditions. Also, three state-of-the-art rPPG algorithms from the literature were selected, implemented and released as open source free software. After a thorough, unbiased experimental evaluation in various settings, it is shown that none of the selected algorithms is precise enough to be used in a real-world scenario.