Real-time face recognition method based on deep neural network

Abstract

The invention provides a real-time face recognition method based on a deep neural network and adjacent element analysis. According to the invention, at first, a multi-layer neural network is practiced through a large-scale face database having the advantage of good diversity, wherein layers besides the last layer are non-linear layers, and the tail layer is a linear layer; then, the obtained network is practiced continuously on the basis of a hybrid face database through the supervised adjacent element analysis method to make the network has more deep understanding of face images so as to achieve the purposes of shorting the face image distance between same individuals and increasing the face image distance between different individuals; and finally, in the actual face recognition stage, the invention provides a concept of 'search radius', so the recognition time can be shortened on the premise of ensuring the recognition rate to realize real-time face recognition. According to the invention, the advantage of high recognition rate can be realized, and at the same time, according to the invention, the advantage of fast recognition speed can be realized, so that the methof of the invention is suitable for being applied in real-time face recognition tasks.

Description

technical field [0001] The invention belongs to the field of pattern recognition, relates to a face recognition method, in particular to a face recognition method capable of performing face recognition tasks in real time. Background technique [0002] As a kind of biometric authentication technology, face recognition has huge market potential and scientific research value due to its characteristics of non-contact, good user experience, and steadily rising recognition rate. Face recognition is a kind of image recognition. The most important and difficult point of image recognition is to give the machine the ability to understand the hidden information contained in the image. As a feature extraction method that can extract deep information from data, the deep neural network can be used for image-based human Face recognition technology has some inspiration. [0003] At present, the deep neural network has made many breakthroughs in the field of pattern recognition: Microsoft u...

AI Technical Summary

Problems solved by technology

[0004] However, few researchers have applied deep neural networks to the field of face recognition. The applicant believes that there are two reasons: on the one hand, the traditional deep neural network + softmax framework requires multiple images to build a model for each individual. The task of face recognition with an uncertain number of categories has poor applicability; on the other hand, the size of the picture required for face recognition is relatively large. Under normal circumstances, a picture of more than 30×30 can achieve satisfactory results, which increases the The Difficulty of Training Deep Network Models

Images