A Convolutional Neural Network Training Method for Face Recognition Based on a Novel Loss Function

Abstract

The invention discloses a face recognition convolutional neural network training method based on a novel loss function, which combines SoftMax loss, cosine similarity loss and Center Loss as the objective function in the face recognition convolutional neural network training process , while increasing the class distance and reducing the intra-class distance, the cosine similarity loss is added to overcome the differences caused by the different measurement methods of face feature comparison during training and testing. Including: 1: Divide face recognition data rows into training sample set and test sample set; 2: Perform data preprocessing on the face images in the training sample set; 3: Construct a face recognition convolutional neural network based on a new loss function Structure; 4: Input the training sample set into the face recognition convolutional neural network for training; 5: Save the face recognition model parameters; 6: Use the test sample set after data preprocessing to test the face recognition model.

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