A face recognition method and device based on deep learning

Abstract

The invention discloses a face recognition method based on deep learning. The face recognition method comprises a face recognition model training method and a face recognition model using method. Thebasic idea of model training is to reduce the difference value between similar samples and increase the difference value between non-similar samples so as to achieve accurate identification of the human face. Firstly, a feature extraction network is trained, classification model training is performed after model training is completed, and a softmax classification layer is added after the trained feature extraction network and used for training of the classification network. The features are classified in the softmax layer, taking the distance between the output and the label as a target by theloss function, and obtaining a face recognition model after the training is finished. The face recognition model using method comprises the steps that a face image is input into a face recognition model, a softmax classification result is obtained, and the category represented by the numerical value score highest dimension serial number is the recognition result.

Description

technical field [0001] The invention relates to the field of computer vision, in particular to a face recognition method based on deep learning. Background technique [0002] With the development of deep learning technology and the rapid improvement of computer computing power, the fields of artificial intelligence, computer vision and image processing are developing rapidly. Among them, face recognition, as a classic topic in the field of computer vision, has great research and application value, and has high social demand. The main problem solved by face recognition is that for an input image containing a human face, the algorithm can automatically extract the facial features on the image, and recognize the facial image according to the features, and give the recognition result. [0003] At present, face recognition related technologies have made great progress, and some successful applications have appeared. Traditional face recognition methods include methods based on ...

AI Technical Summary

Problems solved by technology

[0005] In view of the above problems, the present invention proposes a face recognition model training method and device based on deep learning and a face recognition method and device based on deep learning to solve the problems of low face recognition accuracy and slow recognition speed, and expand the The scope of use of the system

Images