Non-intrusive liveness detection by face images

• Published in: Image and vision computing 2009-02, Vol.27 (3), p.233-244
• Main Authors: Kollreider, K., Fronthaler, H., Bigun, J.
• Format: Article
• Language: English
• Subjects: Anti-spoofing measures; Face liveness; Face part models; Liveness detection; Local Gabor decomposition; Motion of lines; Optical flow; Optical flow of lines; Orientation estimation; Retinotopic vision; Support vector machine classification; TECHNOLOGY; TEKNIKVETENSKAP
• ISSN: 0262-8856; 1872-8138; 1872-8138
• DOI: 10.1016/j.imavis.2007.05.004

A technique evaluating liveness in face image sequences is presented. To ensure the actual presence of a live face in contrast to a photograph (playback attack), is a significant problem in face authentication to the extent that anti-spoofing measures are highly desirable. The purpose of the proposed system is to assist in a biometric authentication framework, by adding liveness awareness in a non-intrusive manner. Analyzing the trajectories of certain parts of a live face reveals valuable information to discriminate it against a spoofed one. The proposed system uses a lightweight novel optical flow, which is especially applicable in face motion estimation based on the structure tensor and inputs of a few frames. For reliable face part detection, the system utilizes a model-based local Gabor decomposition and SVM experts, where selected points from a retinotopic grid are used to form regional face models. Also the estimated optical flow is exploited to detect a face part. The whole procedure, starting with three images as input and finishing in a liveness score, is executed in near real-time without special purpose hardware. Experimental results on the proposed system are presented on both a public database and spoofing attack simulations.