Depth convolution wavelet neural network expression identification method based on auxiliary task

Abstract

The invention discloses a depth convolution wavelet neural network expression identification method based on auxiliary tasks, and solves problems that an existing feature selection operator cannot efficiently learn expression features and cannot extract more image expression information classification features. The method comprises: establishing a depth convolution wavelet neural network; establishing a face expression set and a corresponding expression sensitive area image set; inputting a face expression image to the network; training the depth convolution wavelet neural network; propagating network errors in a back direction; updating each convolution kernel and bias vector of the network; inputting an expression sensitive area image to the trained network; learning weighting proportion of an auxiliary task; obtaining network global classification labels; and according to the global labels, counting identification accuracy rate. The method gives both considerations on abstractness and detail information of expression images, enhances influence of the expression sensitive area in expression feature learning, obviously improves accuracy rate of expression identification, and can be applied in expression identification of face expression images.

Description

technical field [0001] The invention belongs to the technical field of image processing, and mainly relates to computer vision recognition, in particular to a deep convolution wavelet neural network expression recognition method based on auxiliary tasks. It can be applied to facial expression recognition to learn and classify expression features. Background technique [0002] Facial expression recognition is a cutting-edge technology in the field of image processing and computer vision. It is a key step from image processing to image analysis. The quality of the segmentation results directly affects the subsequent image analysis, understanding and solving problems. The purpose of facial expression recognition is to study the coding model of human facial expressions, learn and extract the characteristic expressions of human facial expressions, and realize the automatic synthesis, tracking and recognition of human facial expressions by computer. [0003] At present, the tech...

AI Technical Summary

Problems solved by technology

The facial expression recognition method based on the deep learning network has been used by researchers in recent years, especially the deep convolutional neural network in the deep learning network that is good at processing two-dimensional images has been applied to the field of expression recognition by researchers, but In the general sense, deep convolutional neural networks focus on the abstract mapping of images from low-level to high-level to obtain advanced feature expressions, but ignore the texture and detail information of expression images when obtaining advanced feature expression forms

Moreover, the commonly used deep network is generally a single-task deep network, which cannot effectively highlight the main contribution of the expression-sensitive area to the feature expression when learning the features of the expression.

[0004] In the existing facial expression recognition technology, it is mainly the method of feature selection and then classification, but in the feature selection step, the existing feature selection operator cannot efficiently learn the expression features, so that the subsequent classification cannot be obtained. ideal result

In addition, Lv Yadan and others adopted a deep self-encoder network as a classifier, and did not avoid the step of feature selection, which resulted in little improvement in the final classification effect

Images