New robust face anti-spoofing technique

Abstract

Face recognition is one of the main areas of biometric identification and authentication. Face identification consists of face detection and recognition processes. There are a lot of attacks which they can spoof of faces on face detection process. In this paper all attack points between camera and user application are given. According to the attack points, there are three types of anti-spoofing methods. Based on feature level techniques robust anti-spoofing technique is proposed. When intruder uses photo of the registered person, proposed anti-spoofing technique easily detects. This anti-spoofing technique detects fake face based on pixel value between face and background space.