Human face identification method

Abstract

The invention relates to a human face identification method. The method comprises the following steps of 1, reading a human face image sample data set; 2, establishing a deep convolutional neural network, wherein a residual error unit is introduced in the deep convolutional neural network; 3, updating parameters of the deep convolutional neural network by utilizing a gradient descend algorithm, and firstly mapping human face images of the sample data set into 512-dimension eigenvectors through the deep convolutional neural network; calculating a loss function and a gradient of the loss function, and updating the parameters of the deep convolutional neural network according to whether a gradient descend distance of the loss function is smaller than a preset threshold or not, wherein the loss function is formed by weighting a Softmax function and an A-softmax function; and 4, performing human face identification through the deep convolutional neural network subjected to the parameter updating. Not only the between-class distance but also the within-class distance are considered, so that the human face identification rate is increased.

Description

technical field [0001] The invention relates to a face recognition method, which belongs to the technical field of artificial intelligence. Background technique [0002] In recent years, the face recognition technology based on deep learning has continued to develop, and the recognition rate on the open source face data test set LFW has been continuously refreshed. At the same time, there are some factors that restrict the improvement of the recognition rate: [0003] 1) Acquisition and purification of massive training data. In the training process of the deep learning model, a large number of effective face training samples are relied on to improve the recognition accuracy. In theory, the more data, the stronger the generalization ability of the model. At present, the mainstream open source face recognition training sets include VGG2, Ms-Celeb-1M, etc., but the above data sets can only meet the training of shallow models, and if the two data sets are directly merged, the ...

AI Technical Summary

Problems solved by technology

[0006] In summary, the current face recognition solutions have problems such as lack of training sample set data, insufficient model performance, and low recognition accuracy.

Images