Eyeblink-based Anti-Spoofing in Face Recognition from a Generic Webcamera

Pan, Gang; Sun, Lin; Wu, Zhaohui; Lao, Shihong

doi:10.1109/iccv.2007.4409068

Cited by 564 publications

(349 citation statements)

References 22 publications

Supporting

Mentioning

342

Contrasting

Unclassified

Order By: Relevance

“…Motion analysis is therefore, less dependent on specific re-capturing artifacts explored in texture processing, being potentially able to generalize better. For example, work in [14] and [9] bring a real-time liveness detector specifically design to counter photo-spoofing using spontaneous eye-blinks (supposed to occur once every 2-4 seconds in humans). The system was evaluated on a, currently inaccessible, disjoint dataset of short video clips of eye-blinks and spoofing attempts using photographs.…”

Section: Literature Surveymentioning

confidence: 99%

Motion‐based counter‐measures to photo attacks in face recognition

2014

View full text Add to dashboard Cite

Identity spoofing is a contender for high-security face recognition applications. With the advent of social media and globalized search, our face images and videos are wide-spread on the internet and can be potentially used to attack biometric systems without previous user consent. Yet, research to counter these threats is just on its infancy -we lack public standard databases, protocols to measure spoofing vulnerability and baseline methods to detect these attacks. The contributions of this work to the area are three-fold: firstly we introduce a publicly available PHOTO-ATTACK database with associated protocols to measure the effectiveness of counter-measures. Based on the data available, we conduct a study on current state-of-the-art spoofing detection algorithms based on motion analysis, showing they fail under the light of these new dataset. By last, we propose a new technique of countermeasure solely based on foreground/background motion correlation using Optical Flow that outperforms all other algorithms achieving nearly perfect scoring with an equal-error rate of 1.52% on the available test data. The source code leading to the reported results is made available for the replicability of findings in this article.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Motion‐based counter‐measures to photo attacks in face recognition

2014

View full text Add to dashboard Cite

show abstract

“…In [19], Pan et al extended upon the work in [17] by adding counter-measures to include a scene context matching in stationary face-recognition systems. For this, the authors analyze inside face cues such as eye blinking and outside face cues, since the background scene is known by the recognition system.…”

Section: Related Workmentioning

confidence: 99%

“…Considering behavior modeling, some works have focused on eye blinking [17], [18] and small movements of parts of the head and face [9] to detect specifically photo-based spoofing. Considering that a person blinks approximately once every two to four seconds, Pan et al [17] proposed the use of an undirected conditional random field framework to represent eye blinking from hidden Markov models that relax the independence assumption of generative modeling, with the advantage that the method allows to relax the assumption of conditional independence of the observed data.…”

Section: Related Workmentioning

confidence: 99%

Video-Based Face Spoofing Detection through Visual Rhythm Analysis

Pinto

Pedrini

Schwartz

et al. 2012

2012 25th SIBGRAPI Conference on Graphics, Patterns and Images

View full text Add to dashboard Cite

Fig. 1. Given a training set consisting of videos of valid accesses, video-based spoofs, and a video for testing, first we extract a noise signature of every video (training and testing) and calculate the Fourier Spectrum on logarithmic scale for each video frame. Thereafter, we create visual rhythms for each video and train a machine learning classifier using either the pixel intensities directly as features or a summarized version of the visual rhythms using gray level co-occurrence matrices. With a trained classifier, we are able to test a visual rhythm for a given video under investigation and point out whether it is a valid access or a video-based spoof.Abstract-Recent advances on biometrics, information forensics, and security have improved the accuracy of biometric systems, mainly those based on facial information. However, an ever-growing challenge is the vulnerability of such systems to impostor attacks, in which users without access privileges try to authenticate themselves as valid users. In this work, we present a solution to video-based face spoofing to biometric systems. Such type of attack is characterized by presenting a video of a real user to the biometric system. To the best of our knowledge, this is the first attempt of dealing with video-based face spoofing based in the analysis of global information that is invariant to video content. Our approach takes advantage of noise signatures generated by the recaptured video to distinguish between fake and valid access. To capture the noise and obtain a compact representation, we use the Fourier spectrum followed by the computation of the visual rhythm and extraction of the graylevel co-occurrence matrices, used as feature descriptors. Results show the effectiveness of the proposed approach to distinguish between valid and fake users for video-based spoofing with nearperfect classification results.

show abstract

“…In [11] three different liveness detection solutions where proposed: (a) liveness detection by using a challenge and response method such as eye-blinking (b) by analysing face texture on high quality images, and (c) by combining two or more biometrics for example speech and face recognition together. A liveness detection test against photo spoofing was proposed in [8] based on the analysis of spontaneous eye blinking behaviour. Another liveness detection test against photo spoofing was proposed in [13], using the differences in the reflective properties between a real human face and a photograph of it to discriminate between them.…”

Section: Liveness Testsmentioning

confidence: 99%