A face recognition convolutional neural network training method based on a novel loss function

Abstract

The invention discloses a face recognition convolutional neural network training method based on a novel loss function. Put SoftMax loss, cosine similarity loss, Center Loss are combined used as the objective function in the training of a convolutional neural network for face recognition. The loss of cosine similarity is added to overcome the difference caused by different measurement methods of face feature alignment in training and testing while the class spacing is enlarged and the intra-class distance is reduced. The method includes such steps as 1, dividing face recognition data into training sample set and a test sample set; 2, carrying out data preprocessing on the face images in the training sample set; 3, constructing a new convolutional neural network structure for face recognition based on a new loss function; 4, inputting that training sample set into a face recognition convolution neural network for training; 5, saving that parameters of the face recognition model; 6, testing the face recognition model by using the test sample set after data preprocessing.

Description

technical field [0001] The invention belongs to the field of deep learning for extracting facial features by a deep neural network, relates to technologies such as neural networks and pattern recognition, and in particular relates to a face recognition convolutional neural network training method based on a new loss function. Background technique [0002] In recent years, with the rapid development of computer technology, automatic face recognition technology has been extensively researched and developed. Face recognition has become one of the most popular research topics in pattern recognition and image processing in the past 30 years. The purpose of face recognition is to Extract the personalized features of people from face images, and use them to identify people's identities. [0003] Face recognition has always been a hot spot in the direction of pattern recognition. There are mainly four face recognition methods: methods based on geometric features, methods based on mo...

AI Technical Summary

Problems solved by technology

All these improved algorithms are based on a core idea: enhance inter-class differences and reduce intra-class differences, but the design principles of these loss functions only consider the cosine angle or Euclidean distance between the weight vector and the face feature vector, etc., Without considering the difference caused by the two face feature vectors in the training process

Images