Face recognition method and device

Abstract

The invention relates to the technical field of artificial intelligence, and provides a face recognition method and device, and the method comprises the steps: obtaining a to-be-recognized face image; inputting the face image to a pre-trained face recognition model, and utilizing the face recognition model to process the face image to extract face features of the face image, wherein the face recognition model comprises at least one feature extraction network, the feature extraction network sequentially quantizes, convolves and inversely quantizes an input feature map, and the first parameter adopted by the quantization and the inverse quantization is determined according to the channel number of the input feature map and the preset channel group number; and performing face recognition on the face image according to the face features. According to the method, the convolution operation speed is increased, precision calculation reduction caused by numerical value overflow in the convolution operation process is avoided, and finally the high efficiency and accuracy of face recognition are guaranteed.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a face recognition method and device. Background technique [0002] The convolutional neural network is widely used in face recognition, and the calculation of the convolutional layer in the forward propagation of the convolutional neural network will account for 90% of the calculation of the entire network. Generally, the high-precision convolutional neural network contains The large number of parameters leads to relatively high computational intensity, which cannot meet the needs of face recognition application scenarios with high real-time response requirements. [0003] Although the existing acceleration methods for convolutional neural networks can increase the computing speed of convolutional neural networks and thus improve the efficiency of face recognition, the calculation accuracy will decrease due to value overflow during the accelerated computi...

AI Technical Summary

Problems solved by technology

[0002] The convolutional neural network is widely used in face recognition, and the calculation of the convolutional layer in the forward propagation of the convolutional neural network will account for 90% of the calculation of the entire network. Generally, the high-precision convolutional neural network contains The large number of parameters leads to relatively high computational intensity, which cannot meet the needs of face recognition application scenarios that require high real-time response

[0003] Although the existing acceleration methods for convolutional neural networks can increase the computing speed of convolutional neural networks and thus improve the efficiency of face recognition, the calculation accuracy will decrease due to value overflow during the accelerated computing process, and eventually Affected the accuracy of face recognition

Images