浅析深度学习生物识别反欺诈辅助算法

Analysis on Assistant Algorithm of Biological Identification and Anti-fraud in In-depth Learning

近年来生物识别技术在安全认证领域发挥着越来越重要的作用,但仅依赖深度学习的人脸识别技术在安全性方面还存在一定欠缺。为了在一定程度上解决单纯采用深度学习系统进行人脸识别的安全问题,提出一种基于人脸图像频域纹理的2D人脸反欺诈辅助算法,算法能够判断摄像头采集的图像是否经过二次翻拍,从而得出图像是否为真人,进而达到提升人脸识别安全性的目的。

In recent years,biometrics technology is playing an increasingly important role in the field of security authentication,but face recognition based on in-depth learning has some defects in security.In order to solve the security problem of face recognition using in-depth learning system to a certain extent,a 2D face anti-fraud auxiliary algorithm based on face image frequency domain texture is proposed.The algorithm can determine whether the image collected by the camera has undergone secondary remake.Therefore,it can be concluded whether the image is a real person,and then the purpose of improving the security of face recognition is achieved.