Human face identification method and apparatus

Abstract

The invention discloses a human face identification method and apparatus, and belongs to the field of human face identification. The method comprises: performing feature extraction on a to-be-identified human face image by using a plurality of pre-trained convolutional neural networks to obtain a plurality of sub-feature vectors of the to-be-identified human face image, wherein the sub-feature vectors of the to-be-identified human face image are same in number of dimensions; normalizing the sub-feature vectors of the to-be-identified human face image; performing addition on the normalized sub-feature vectors of the to-be-identified human face image, and multiplying the sum of the normalized sub-feature vectors by a coefficient to obtain a union feature vector of the to-be-identified human face image; and performing human face identification by using the union feature vector of the to-be-identified human face image or / and the sub-feature vectors of the to-be-identified human face image. According to the human face identification method and apparatus, the training time of the convolutional neural networks is shortened, the over-fitting of the convolutional neural networks is avoided, and the operation is simple and convenient; and identification modes are more diversified and the accuracy is higher.

Description

technical field [0001] The invention belongs to the field of face recognition, in particular to a method and device for face recognition. Background technique [0002] With the rise of deep learning, especially the deepening of deep convolutional neural network research, a large number of network models based on convolutional neural network (CNN) have been applied to image processing and image recognition, especially face recognition. , and achieved remarkable results. [0003] The unique feature of convolutional neural network is that it can automatically obtain feature expression through learning without manual intervention. However, the resulting feature separability and interpretability depend on the depth of the network (the number of layers in the network). Therefore, the deep convolutional neural network came into being. The deep convolutional neural network generally undergoes multiple convolution operations, activation operations, and downsampling operations to ob...

AI Technical Summary

Problems solved by technology

[0006] It can be seen from the above that for a given deep convolutional neural network, in order to prevent overfitting, it is necessary to increase the training samples, but increasing the training samples will make the training time longer, so that the training time and the overfitting problem cannot be balanced

Images