Deep learning-based human face identification method for real scene

Abstract

The invention provides a deep learning-based human face identification method for a real scene, which is proposed for solving the problem that an existing human face identification method for the realscene only can eliminate influence of single factor and cannot eliminate influence of factors of pose, illumination and the like. The method comprises the steps of predicting human face positions ofimages in a training database by using an existing human face detector, and capturing and storing real human face and non human face images; according to the human face images and the non human face images, performing down-sampling to obtain corresponding low-resolution images; building a generative adversarial network, wherein the generative adversarial network comprises a generator and an identifier, and the generator further comprises an up-sampling network and an optimization network; training the generative adversarial network by using high-resolution human face and non human face imagesand the corresponding low-resolution human face and non human face images; and according to scores of the identifier to candidate human face regions obtained from the existing human face detector, marking the human face positions in the input images. The method is suitable for human face identification detection.

Description

technical field [0001] The invention relates to the field of face recognition, in particular to a face recognition method based on deep learning in a real scene. Background technique [0002] With the development of e-commerce and other applications, face recognition has become the most potential biometric authentication method. This application background requires automatic face recognition systems to have certain recognition capabilities for face images in real scenes. Therefore, Faced with a series of problems, face detection began to be regarded as an independent subject by researchers. In addition, face recognition technology in real scenes has urgent application needs in many fields such as security, criminal investigation, search and rescue. [0003] Based on the fact that face detection has very important basic research value and urgent application requirements in the field of machine vision, the corresponding technologies for face detection are also constantly bein...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the face recognition method under the existing real scene can only solve the influence of a single factor, but can not solve the influence of other influencing factors such as posture, illumination; And the face recognition method based on the face alignment method can alleviate The influence of posture, but it cannot solve the shortcomings of other factors such as scale and blur, and proposes a face recognition method based on deep learning in real scenes, including:

Images