Face representation attack detection method based on full-size depth map supervision

Abstract

The invention discloses a face representation attack detection method based on full-size depth map supervision. The method comprises the following steps: constructing a face representation attack detection model based on full-size depth map supervision; inputting a to-be-detected face picture into the trained face representation attack detection model, acquiring a full-size prediction depth map which is identical to the to-be-detected face picture in width and height, wherein each pixel value on the full-size prediction depth map is a depth prediction value of a corresponding pixel point of the to-be-detected face picture; and taking an average depth prediction value of the full-size prediction depth map as a final score, and comparing the final score with a preset discrimination threshold to obtain a detection result. The full-size depth map is adopted as a label for supervised modeling, the shallow-layer features and the deep-layer features of the input face image are fused to obtain the full-size prediction depth map, the detection precision is high, and the invention can adapt to reality detection scenes under different illumination and acquisition equipment conditions.

Description

technical field [0001] The invention relates to the technical fields of image processing and biological security, in particular to a face representation attack detection method based on full-scale depth map supervision. Background technique [0002] Face recognition technology has been widely used at present. In addition to providing legitimate users with a good experience in the identity authentication stage, it also provides opportunities for criminals to infringe upon rights. Attempts to use legitimate user's face photos, videos and other means to borrow the user's identity through the operation of the face recognition system are called face representation attacks. The method of detecting such attacks is called face representation attack detection. Therefore, the face recognition system not only needs to judge whether the face picture obtained by the camera belongs to the legitimate user, but also needs to judge whether the picture is a real face directly obtained by tak...

AI Technical Summary

Problems solved by technology

At present, there are some studies that introduce the depth map as label information, but these studies compress the label depth map by several times. The common one is to compress it from 256*256 to 32*32, which loses a lot of label information, resulting in Network fails to fully utilize depth map labels for supervised learning

Images