Face identification method based on random pooling convolutional neural network

Abstract

The invention discloses a face identification method based on a random pooling convolutional neural network. According to the method, the characteristics of a face image are quickly extracted by the random pooling convolutional neural network and cascaded to realize face identification; selection strategies and steps of new pooling values are adopted in a process of creating the convolutional neural network and then supervised training is carried out by a softmax classifier; the probability distribution used in a sampling process is based on energy, and the effect of optimizing increment of the calculation speed of the characteristics extracted by the convolutional neural network and generalization application of a convolutional neural network training result can be achieved; the convolutional neural network training based on random pooling is simple and high in accuracy, and can promote wide application of random pooling in the process of extracting the face identification characteristics.

Description

technical field [0001] The invention belongs to the fields of machine learning and face recognition, and relates to a face recognition method based on a random pooling convolutional neural network. Background technique [0002] As a biometric identification technology, face recognition has become a research hotspot in the field of image processing and pattern recognition, and has been widely studied in the fields of public security, human-computer interaction and identity authentication. At present, the research on feature extraction of face recognition at home and abroad mainly focuses on two directions: manually extracting corresponding features and constructing neural network to automatically extract features. The traditional convolutional neural network has many parameters. One of the main problems is the computational complexity and time overhead. The dimension of the feature matrix that needs to be calculated is large, which is not conducive to the training of the clas...

AI Technical Summary

Problems solved by technology

The existing pooling technology mainly uses the mean or maximum function as the pooling method, in which the mean function pooling method will reduce the influence of larger convolution values, while the maximum function pooling method will make some convolutions The value is too representative of the entire pooled square convolution vector to cause overfitting of the training set, which is not conducive to the generalization of the entire convolutional neural network to face recognition problems

Images