Face recognition method, device and system and storage medium

Abstract

The invention relates to a face recognition method, device and system and a storage medium, and the method comprises the steps: recognizing at least two to-be-recognized images with different sizes through at least two first face recognition models to acquire each first face image in the to-be-recognized images; recognizing all the first face images through a second face recognition model to obtain each second face image in the first face images; and recognizing all the second face images through a third face recognition model to obtain a face recognition result. According to the embodiment of the invention, the invention achieves the recognition of the original to-be-recognized images at different scales through the multi-level face recognition model. The face images of the to-be-recognized images at different scales are extracted. By the second face recognition model and the third face recognition model, further recognition is carried out on the face images obtained by the to-be-recognized image under different scales, the accurate face image in the to-be-recognized image is determined, and the face recognition effect is improved.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to a face recognition method, device, system and storage medium. Background technique [0002] With the advancement of technology, biometric identification technology is increasingly used in daily life. As a biometric identification technology, face recognition technology has been widely used due to its characteristics of easy collection, non-contact, and high recognition rate. Face liveness detection technology is an important part of the face recognition system. By distinguishing whether the object in front of the camera is a real person or a prosthesis, the security of the face recognition system can be effectively improved. [0003] Face detection and recognition in edge devices is a difficult and hot topic in current research. The conventional method is to deploy the face detection model and face recognition model trained on the PC side to the front-end edge...

AI Technical Summary

Problems solved by technology

The conventional method is to deploy the face detection model and face recognition model trained on the PC side to the front-end edge device, accelerate based on the arm instruction set on the edge device, and use the neural network to complete the image face detection and recognition functions. These solutions are The program of software accelerated face recognition, under the acceleration of simple instructions, although the calculation efficiency of the system is accelerated, the final recognition effect will not change much, and users cannot obtain accurate face recognition results

Images