Face recognition method

Abstract

The invention provides a face recognition method. The face recognition method comprises the following steps: S1, obtaining face training test resources from a public data set; S2, preprocessing the image; S3, inputting the processed face data set into a convolutional neural network of a novel network structure of an improved NVM module to obtain a trained lightweight convolutional neural network;S4, inputting the face images in the test set into the trained lightweight convolutional neural network model, and judging whether the lightweight model can be accurately verified to effectively classify the face data set or not.

Description

technical field [0001] The invention relates to a face recognition method. Background technique [0002] With the advent of the 5G era, with the Internet of Things and big data technologies gradually becoming more mature, the rate of information transmission continues to accelerate, and the range of smart terminals that can help us in our lives is becoming wider and wider. Among them, intelligent identification, intelligent classification, and intelligent calculation are the most widely used. The intelligent recognition of images and videos has become an indispensable part of our lives. [0003] As an important source of information to capture human activities, facial recognition has promoted the development of face recognition technology. It is more and more widely used in daily life, for example, commercial face payment system, law enforcement system and other applications. There have been many face pattern recognition methods, such as principal component analysis (PCA)...

AI Technical Summary

Problems solved by technology

However, due to the characteristics of the neural network, in order to obtain higher accuracy, we are constantly increasing the depth and complexity of the network, the number of internal parameters, and the nonlinear mapping are becoming larger and larger, so perhaps a very deep network The structure will have good calculation results in competitions and data representation, but in practical applications, it is often limited by the storage space, computing power, and calculation speed of the terminal.

[0005] However, in daily face recognition algorithms, we often have to obtain learning results in milliseconds, and these devices often have limited processor performance, and cannot spend a lot of time training operations like in the laboratory.

Therefore, the practicality of convolutional neural networks in face recognition is greatly limited.

Images