Face recognition method based on a mutual exclusion regularization technology

Abstract

The invention discloses a face recognition method based on a mutual exclusion regularization technology, and belongs to the technical field of image processing, and the method comprises the steps: firstly importing a screened and calibrated face image data set into a model; Performing feature extraction on the input image data by using a residual neural network to obtain a feature vector; calculating a classification probability by using the feature vector and the classification parameter matrix to obtain an identification vector; using an A-Softmax loss function calculates a loss difference between the identification vector and the label and using the loss difference as a gradient to carry out back propagation so as to update parameters in the feature extraction network; calculating a partial derivative of the mutually exclusive regularization term with respect to the classification parameter matrix and updating the classification parameter matrix using the partial derivative; considering The intra-class compactness and the inter-class separability at the same time, the method has more practical significance for application of a face recognition model in an open environment, denseclustering of intra-class data and discrete distribution of inter-class data under a face recognition task can be achieved at the same time through the method, and the method is more practical and universal compared with an existing method.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a face recognition method based on mutual exclusion regularization technology. Background technique [0002] Face recognition is one of the most widely studied topics in computer vision. Recently, Convolutional Neural Networks (CNN) have become the workhorse method in the field of artificial intelligence research and have achieved remarkable progress. Generally, there are two test environments for face recognition in face recognition: open and closed. In an open test environment, the identity category to which the test picture belongs may not exist in the training set data. In a closed test environment, there are corresponding identity categories in both the training dataset and the testing dataset. Because it is impossible to collect all possible identity faces for training, face recognition in the open environment is more challenging and closer to real-wo...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the existing face recognition models and methods only consider the compactness between the same type of features under the face classification problem without considerin...

Images