Facial expression recognition method based on improved deep convolutional generative adversarial network

Abstract

The invention discloses a facial expression recognition method based on an improved deep convolutional generative adversarial network. The method comprises the steps of 1, acquiring a facial image data set and performing preprocessing; 2, constructing a generative adversarial network, and training the network by using the preprocessed face data set to obtain a composite image; 3, constructing a facial expression classification network, wherein a facial image data set with expression labels is used for training; and 4, connecting the generative adversarial network and the expression classification module to form a whole expression recognition network model, cutting a face image to be recognized into a set size, inputting the face image into the face expression recognition network model, and obtaining an output result to determine a face expression in the face image. The improved generative adversarial network is used for processing the original face image, and finer effective information can be extracted, so that the face expression recognition accuracy is improved.

Description

technical field [0001] The invention relates to the related fields of deep learning and image processing, in particular to a facial expression recognition method based on an improved deep convolutional generative confrontation network. Background technique [0002] According to research, most of human emotion expression is transmitted through facial expressions, and human expression recognition technology is of great significance in fields such as human-computer interaction, emotion analysis, and public security monitoring. At present, human facial expressions are generally divided into seven categories, namely "angry, disgusted, scared, happy, sad, surprised, and neutral". The traditional facial expression recognition method extracts features manually and classifies them. At the same time, the traditional technology has shortcomings such as poor robustness. With the development of computer technology, deep learning has become one of the research hotspots in recent years. T...

AI Technical Summary

Problems solved by technology

[0003] However, there are certain problems in the facial expression recognition method based on deep learning in the prior art. The existing expression recognition method usually needs to directly extract features from the face image, but in real life, the image may have uneven light and image Due to problems such as blurring and occlusions on the face, feature information cannot be extracted well

At the same time, the training strategy in the recognition algorithm may lead to overfitting problems, reduce the performance of the target database, and reduce the accuracy of face recognition

Images