Face Feature Extraction and Recognition Based on Lighted Deep Convolutional Neural Network

Abstract

Face recognition is one of the most challenging research fields in image processing, pattern recognition and artificial intelligence, and its practical application has a bright future. Face is vulnerable to illumination and expression factors in the process of image acquisition. The traditional machine learning method for extracting face features usually requires high clarity of face images to achieve ideal results. Face feature extraction and recognition based on deep learning method can effectively solve this kind of problem, but the recognition rate is greatly improved, at the same time, the size of the network and the difficulty of training are also sharply increased. It does not meet the increasingly lightweight requirements of the network. This paper studies the current mainstream DCNN architecture, especially MobileNet and ShuffleNet at light-weight mobile level. Some high-efficiency and practical structural features of convolution are summarized; A Nonlinear separable deep convolutional neural network X-Net is designed; Focusing on the loss of the sample in the real face dataset, focus loss is introduced to reduce the effect of sample deviation on network fitting. The experimental results show that the feature extraction based on deep convolutional neural network in this paper can use dynamic library DLL to play an effective role in practical commercial projects.