Face verification method and device, computer equipment and storage medium

Abstract

The invention provides a face verification method and device, computer equipment and a storage medium, belongs to the field of face recognition, and specifically comprises the steps: judging whether ato-be-verified target corresponding to a face image is a living body or not according to the shot infrared image and a depth image when the fact that the face image exists in the shot infrared imageis judged; when it is judged that the to-be-verified target is a living body, extracting the face image from a shot RGB image; when it is judged that the face image meets a first preset processing condition and a second preset processing condition, extracting face key points from the shot RGB image; performing face correction on the RGB image, the depth image and the infrared image according to the face key points, and extracting corrected target face features; and comparing the target face features with sample face features of sample candidates in a face database to obtain a verification result corresponding to the to-be-verified target. Through the processing scheme of the invention, the cost is reduced, and the face recognition verification accuracy is improved.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a face verification method, device, computer equipment and storage medium. Background technique [0002] As an important machine vision technology, face recognition plays a major role in the field of artificial intelligence. In many application scenarios (such as door locks, access control, gates, etc.), there are high requirements for device power consumption, attack defense capabilities, recognition accuracy and pass rate. Currently, two types of cameras are usually used for detection. For example, images captured by an RGB camera are used for face recognition, and images captured by an IR camera are used for live detection. IR cameras tend to rely too much on feedback video images. Once the camera is attacked, for example, the attacker will If the recorded video image replaces the video image collected by the camera, the liveness detection will fail or the liveness detection w...

AI Technical Summary

Problems solved by technology

Currently, two types of cameras are usually used for detection. For example, images captured by an RGB camera are used for face recognition, and images captured by an IR camera are used for live detection. IR cameras tend to rely too much on feedback video images. Once the camera is attacked, for example, the attacker will The recorded video image replaces the video image collected by the camera, which will lead to the failure of the live detection or the wrong detection of the live body, which will bring losses to the user and lower security

Images