Face anti-spoofing with multifeature videolet aggregation

Siddiqui, Talha Ahmad; Bharadwaj, Samarth; Dhamecha, Tejas I.; Vatsa, Mayank; Singh, Richa; Ratha, Nalini K.

doi:10.1109/icpr.2016.7899772

Cited by 90 publications

(32 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the increasing number of pub-150 lic benchmark databases, numerous passive software-based approaches have been proposed for face anti-spoofing. In general, passive methods based on analyzing different facial properties, like frequency content [33,34], texture [10,35,36,37,38,39] and quality [40,41,42], or motion cues, like eye blinking 155 [43,44,45,46], facial expression changes [27,44,45,46], mouth movements [27,44,45,46], or even color variation due to blood circulation (pulse) [47], to discriminate face artifacts from genuine ones. Passive software-based methods have shown impressive results on the publicly available datasets but 160 the preliminary cross-database tests, like [11,32], revealed that the performance is likely to degrade drastically when operating in unknown conditions.…”

mentioning

confidence: 99%

On the generalization of color texture-based face anti-spoofing

Boulkenafet

Komulainen

Hadid

2018

Image and Vision Computing

View full text Add to dashboard Cite

Despite the significant attention given to the problem of face spoofing, we still lack generalized presentation attack detection (PAD) methods performing robustly in practical face recognition systems. The existing face anti-spoofing techniques have indeed achieved impressive results when trained and evaluated on the same database (i.e. intra-test protocols). Cross-database experiments have, however, revealed that the performance of the state-of-the-art methods drops drastically as they fail to cope with new attacks scenarios and other operating conditions that have not been seen during training and development phases. So far, even the popular convolutional neural networks (CNN) failed to derive well-generalizing features for face anti-spoofing. In this work, we explore the effects of different factors, such as acquisition condition and presentation attack instrument (PAI) variation, on the generalization of color texture-based face anti-spoofing. Our extensive cross-database evaluation of seven color texture-based methods demonstrate that most of the methods are unable to generalize to unseen spoofing attack scenarios. More importantly, the experiments show that some facial color texture representations are more robust to particular PAIs than others. From this observation, we propose a face PAD solution of attack-specific countermeasures based solely on color texture analysis and investigate how well it generalizes under display and print attacks in different conditions. The evaluation of the method combining attack-specific detectors on three benchmark face anti-spoofing databases showed remarkable generalization ability against display attacks while print attacks require still further attention.

show abstract

mentioning

confidence: 99%

On the generalization of color texture-based face anti-spoofing

Boulkenafet

Komulainen

Hadid

2018

Image and Vision Computing

View full text Add to dashboard Cite

show abstract

“…Early studies allow user to interact in front of devices such as blinking eyes, nodding head, etc., but the interactions reduce the quality of experiences. Siddiqui et al [13] used temporal evidence aggregation over face region and scene of video images, which performs well on 2D face attack datasets due to the synthesized multi-features, but fails to judge the 3D realistic masks. In addition, Long Short Term Memory (LSTM) [14] can recurrently learn features to obtain context information, but it suffers from the heavily computational burden.…”

Section: A Face Anti-spoofingmentioning

confidence: 99%

Data-Fusion-Based Two-Stage Cascade Framework for Multimodality Face Anti-Spoofing

Liu

Wei²,

Lei

et al. 2022

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

Existing face anti-spoofing models using deep learning for multi-modality data suffer from low generalization in the case of using variety of presentation attacks such as 2D printing and high-precision 3D face masks. One of the main reasons is that the non-linearity of multi-spectral information used to preserve the intrinsic attributes between a real and a fake face are not well extracted. To address this issue, we propose a multi-modility data based two-stage cascade framework for face anti-spoofing. The proposed framework has two advantages. Firstly, we design a two-stage cascade architecture that can selectively fuse lowlevel and high-level features from different modalities to improve feature representation. Secondly, we use multi-modality data to construct a distance-free spectral on RGB and infrared (IR) to augment the non-linearity of data. The presented data fusion strategy is different from popular fusion approaches, since it can strengthen discrimination ability of network models on physical attribute features than identity structure features under certain constraints. In addition, a multi-scale patch based weighted finetuning strategy is designed to learn each specific local face region. Experimental results show that the proposed framework achieves better performance than other state-of-the-art methods on both benchmark datasets and self-established datasets, especially on multi-material masks spoofing.

show abstract

“…An input RGB image was converted into the HSV space for calculating color moments, and the concatenated feature vector was input to an SVM for classification. Siddiqui et al [159] proposed a multi-feature face spoof detection algorithm consisting of a multi-scale configuration of LBP and Histogram of Oriented Optical Flow (HOOF) features classified using an SVM. Experiments were performed using spoofed and bonafide video samples, wherein intra-feature and inter-feature fusion was performed at the score level.…”

Section: Biometric Fusion and Presentation Attack Detectionmentioning

confidence: 99%

“…Description 2012 Marasco et al [12] Different frameworks for integrating a spoof detection module with a recognition system 2015 Wen et al [154] Ensemble of SVMs on reflection, blurriness, chromatic moment, and color diversity 2015 Raghavendra et al [155] Feature level concatenation with Light Field Camera based features 2015 Arashloo et al [156] Fused MBSIF-TOP and MLPQ-TOP using SR-KDA 2016 Ding et al [89] Bayesian Belief Networks for fusing match scores with liveness scores 2016 Boulkenafet et al [157] CoALBP and LPQ features in HSV and YCbCr colour space 2016 Patel et al [158] Concatenation of color moments and LBP features 2016 Siddiqui et al [159] Inter-feature and intra-feature score-level fusion of multi-scale LBP and HOOF features 2016 Ding and Ross [160] Fusion of multiple one-class SVMs to improve generalizability of a fingerprint spoof detector 2017 Toosi et al [161] Comparative study of different fusion techniques on ten fingerprint features 2017 Korshunov and Marcel [162] Studies impact of score fusion on presentation attack detection for voice 2018 Komeili et al [163] Fusion of ECG recognition and fingerprint spoof detection 2018 Yadav et al [164] Fusion of (VGG features+PCA) with (RDWT+Haralick) features and neural network 2018 Sajjad et al [165] Two-tier authentication system for recognition and spoof detection 2018 Chugh et al [166] CNN based spoof detection on fingerprint patches fused a CNN with RNN in order to extract pseudo-depth images and a remote photoplethysmography (RPPG) signal from an input face video. The extracted information were then fused for face anti-spoofing.…”

Section: Year Authorsmentioning

confidence: 99%

A comprehensive overview of biometric fusion

2019

Self Cite

View full text Add to dashboard Cite

The performance of a biometric system that relies on a single biometric modality (e.g., fingerprints only) is often stymied by various factors such as poor data quality or limited scalability. Multibiometric systems utilize the principle of fusion to combine information from multiple sources in order to improve recognition accuracy whilst addressing some of the limitations of singlebiometric systems. The past two decades have witnessed the development of a large number of biometric fusion schemes. This paper presents an overview of biometric fusion with specific focus on three questions: what to fuse, when to fuse, and how to fuse. A comprehensive review of techniques incorporating ancillary information in the biometric recognition pipeline is also presented. In this regard, the following topics are discussed: (i) incorporating data quality in the biometric recognition pipeline; (ii) combining soft biometric attributes with primary biometric identifiers; (iii) utilizing contextual information to improve biometric recognition accuracy; and (iv) performing continuous authentication using ancillary information. In addition, the use of information fusion principles for presentation attack detection and multibiometric cryptosystems is also discussed. Finally, some of the research challenges in biometric fusion are enumerated. The purpose of this article is to provide readers a comprehensive overview of the role of information fusion in biometrics.

show abstract

Face anti-spoofing with multifeature videolet aggregation

Cited by 90 publications

References 17 publications

On the generalization of color texture-based face anti-spoofing

On the generalization of color texture-based face anti-spoofing

Data-Fusion-Based Two-Stage Cascade Framework for Multimodality Face Anti-Spoofing

A comprehensive overview of biometric fusion

Contact Info

Product

Resources

About