Gender recognition method based on convolution neural network

Abstract

The invention discloses a gender recognition method based on a convolution neural network, and the method comprises the steps: obtaining a training sample set, and setting gender labels for all human face images; carrying out the preprocessing of each human face image sample, and obtaining Gabor features in different directions at different scales; obtaining a plurality of Gabor feature images, and converting the plurality of Gabor feature images into a one-dimensional feature vector; carrying out the reduction of dimensions, and converting the one-dimensional feature vector into a feature matrix which is matched with the size of an input layer of the convolution neural network; obtaining the convolution neural network according to the feature matrix of the human face image sample and the gender labels through training; extracting the corresponding feature matrix of a to-be-recognized human face image through the same method, inputting the feature matrix into the trained convolution neural network, and obtaining a gender recognition result. The method employs the Gabor features and combines the convolution neural network for the gender recognition, improves the robustness of illumination changes, and improves the recognition rate of gender.

Description

technical field [0001] The invention belongs to the technical field of face recognition, and more specifically relates to a gender recognition method based on a convolutional neural network. Background technique [0002] With the development of artificial intelligence technology, the research on face recognition is becoming more and more popular. As a branch technology of face recognition, gender recognition has great research value. Gender recognition is also a kind of pattern recognition, which is similar to general pattern recognition methods, and its main purpose is to find the optimal feature extraction method and optimal classification method. For gender recognition, many researchers have done research on it. For some of these studies, you can refer to the literature Gender Recognition on Real World Faces Based on Shape Representation and Neural Network. Arigbabu et al. used artificial neural network methods for gender recognition on unaligned faces in the face datab...

AI Technical Summary

Problems solved by technology

First of all, in the process of collecting face images, the face images may be collected under different lighting and different equipment, and at the same time, there may be different shooting angles during the collection process. These factors affect the performance of gender recognition. Recognition rate

Images