Face Anti-Spoofing Method with Blinking Eye and HSV Texture Analysis

Abstract

Abstract A face recognition system should recognize faces and detect spoofing attempts with printed face or digital displays. A straightforward method of spoofing prevention is to analyze life signs such as eye blinking. However, this method is vulnerable when dealing with video-based replay attacks. For this reason, this paper proposes a combined method of blink detection with HSV (Hue, Saturation, Value) texture analysis. The anti-spoofing method is designed with two modules, the blinking eye module that evaluates eye openness points and the HSV texture module, which evaluates the texture of the color space from the input media. The test data is taken from the NUAA Photograph Imposter database. The results show that the designed model successfully recognizes 100% spoof-attack without exception.