Generation method of convolutional neural networks and expression recognition method

Abstract

The invention discloses a generation method of convolutional neural networks for conducting expression recognition on the human face in an image, an expression recognition method, calculation equipment and a mobile terminal. The generation method of the convolutional neural network comprises the steps that the first convolutional neural network is established, wherein the first convolutional neural network comprises a first number of processing modules, a first overall average pooling layer and a first classifier which are connected in sequence; according to a pre-acquired facial image data set, the first convolutional neural network is trained, and the first classifier outputs and indicates an expression corresponding to the human face conveniently, wherein the facial image data set comprises multiple pieces of facial image information; the second convolutional neural network is established, wherein the second convolutional neural network comprises a second number of processing modules, a second overall average pooling layer and a second classifier which are connected in sequence; according to the facial image data set, the trained first convolutional neural network and second convolutional neural network are subjected to joint training, and the second classifier outputs and indicates the expression corresponding to the human face conveniently.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method for generating a convolutional neural network for facial expression recognition in an image, a facial expression recognition method, a computing device, and a mobile terminal. Background technique [0002] Expression recognition plays an important role in many real-world scenarios. For example, in online chatting, by recognizing the expressions of the parties involved in the chat and then sending corresponding expression interactions to the other party, the fun of language interaction is enhanced. However, there are many problems in predicting real expressions based on human faces. Factors such as makeup, plastic surgery, one's own physical fitness and living environment can have a significant impact on the judgment of expressions. [0003] At present, facial expression recognition methods are mainly divided into two categories: one is through the extrac...

AI Technical Summary

Problems solved by technology

However, there are many problems in predicting real expressions based on human faces. Factors such as makeup, plastic surgery, physical fitness and living environment can have a significant impact on the judgment of expressions.

[0003] At present, facial expression recognition methods are mainly divided into two categories: one is through the extracted facial features, such as SIFT (Scale-invariant feature transform, scale-invariant feature transform) features, clustering and other processing to achieve expression recognition recognition, but the accuracy can only reach about 50% to 60%, which is far from meeting the needs of actual products; the other type uses CNN (Convolutional Neural Network, Convolutional Neural Network) deep learning method, which can reach more than 95% Accuracy, but if such recognition accuracy is to be achieved, correspondingly, the structure of the CNN-based expression recognition model will be relatively large, with hundreds of megabytes in motion, and the calculation efficiency is low, it is difficult to recognize expressions in real time, and the application on the mobile terminal is extremely limited.

Images