Method and device for carrying out face recognition on user and computer readable storage medium

Abstract

The invention discloses a method for carrying out face recognition on a user. The method comprises the following steps: continuously collecting images of multiple modes; determining whether the face quality of the to-be-recognized face in the images of the plurality of modes acquired in the first acquisition stage meets a first standard or not; if the first standard is met, transmitting the candidate images acquired during the first acquisition stage to a face recognition server; if the first standard is not met, determining whether the face quality of the to-be-recognized face in the images of the multiple modes collected in the first acquisition stage or the second acquisition stage meets a second standard or not, wherein the second standard is lower than the first standard; and transmitting the candidate images acquired during the first acquisition stage or the second acquisition stage to the face recognition server if a second criterion is satisfied. The invention further relates to other methods, devices and computer readable storage equipment. According to the multi-stage face recognition method, face recognition can be carried out on the user more accurately and efficiently.

Description

technical field [0001] One or more embodiments of this specification relate to face recognition, and in particular, to a method, device, and computer-readable storage medium for face recognition. Background technique [0002] Currently, the use of biometrics to identify users is becoming more and more common. Face recognition, also known as facial recognition, portrait recognition, facial recognition, etc., is an important form of biometric recognition. [0003] However, in practical applications, there are many factors that affect the success rate of face recognition. For example, over-exposed light, too dark light, wearing a hat or mask, too long hair, other occlusions, the user looking at the camera from too large an angle, etc., may cause the quality of the face in the collected image to be too poor, resulting in the inability to Accurately recognize faces. [0004] In order to solve this problem, the face recognition device usually prolongs the time for collecting im...

AI Technical Summary

Problems solved by technology

[0005] However, due to factors of the environment itself (for example, the ambient light is too bright or too dark) or because the user is not willing to cooperate (for example, the user is unwilling to take off the hat or mask or adjust the angle, etc.), prolonging the collection time cannot collect images that meet the quality requirements. image

Images