Face recognition based living body detection method and apparatus

Abstract

The invention relates to a face identification based living body detection method and apparatus. The method comprises the steps of: carrying out identity authentication on a to-be-detected user in a to-be-detected crowd through face identification; obtaining a training eye image of the to-be-detected user watching a training sight point, and further extracting training sightline features; obtaining a to-be-detected eye image of the to-be-detected user watching a system random point, and further extracting to-be-detected sightline features; for the to-be-detected user passing the identity authentication, carrying out primary sight point position estimation by adopting an adaptive linear regression algorithm by utilizing a training sight point sequence, the training sightline features and the to-be-detected sightline features; adding the system random point, meeting the predetermined conditions, in the sight point position obtained by primary sight point position estimation into the training sight point sequence to form a new sight point sequence, and carrying out incremental sight point position estimation; and estimating the estimated sight point position according to the incremental sight point position, and carrying out living body judgment by utilizing KL divergence.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a face recognition-based living body detection method and device. Background technique [0002] As an identity authentication technology emerging in recent years, face recognition has achieved great development and has been increasingly widely used in public security, attendance control, credit card identification and other fields. However, traditional face recognition technology is vulnerable to attacks from various false faces, such as photos, videos, and even 3D models. Once the face attack is successful, it may cause heavy losses to users. Therefore, with the development of technology and the needs of information security, adding liveness detection to face recognition systems has attracted more and more attention. [0003] Compared with the real face, the face in the photo is flat, and there are defects such as quality loss and blurring caused by secondary acquisition. The ...

AI Technical Summary

Problems solved by technology

[0006] However, in the existing methods of using line of sight for liveness detection, there are complex detection equipment, such as the need to use infrared cameras or audio input devices, etc., and are only effective for photo attacks, and have no defense capabilities for video attacks that change line of sight. such defects

Images