Recurrent neural network-based discrete emotion recognition method

Abstract

The invention provides a recurrent neural network-based discrete emotion recognition method. The method comprises the following steps: 1, carrying out face detecting and tracking on image signals in a video, extracting key points of faces to serve as deformation features of the faces after obtaining the face regions, clipping the face regions and normalizing to a uniform size and extracting the appearance features of the faces; 2, windowing audio signals in the video, segmenting audio sequence units out and extracting audio features; 3, respectively carrying out sequential coding on the three features obtained by utilizing a recurrent neural network with long short-term memory models to obtain emotion representation vectors with fixed lengths, connecting the vectors in series and obtaining final emotion expression features; and 4, carrying out emotion category prediction by utilizing the final emotion expression features obtained in the step 3 on the basis of a support vector machine classifier. According to the method, dynamic information in the emotion expressing process can be fully utilized, so that the precise recognition of emotions of participators in the video is realized.

Description

technical field [0001] The invention belongs to the field of video signal processing, and in particular relates to a discrete emotion recognition method based on a recursive neural network with a long-short-term memory model, thereby improving the accuracy of the discrete emotion recognition. Background technique [0002] In recent years, researchers at home and abroad have done a lot of research work on discrete emotion recognition, and proposed many effective algorithms for emotion recognition. These methods can be divided into emotion recognition based on static images and emotion recognition based on dynamic videos from the processing strategy. The main framework of video-based emotion recognition work is: first extract the features of each frame image in the video, then maximize these features and obtain emotional features of uniform length, and finally use this feature for emotional classification. The framework uniformly maps feature sequences of different lengths in...

AI Technical Summary

Problems solved by technology

However, this method ignores that emotion expression is a dynamic process, and the dynamic information in emotion expression plays an important role in emotion recognition.

Only through the method of maximum pooling feature sequence, the dynamic information of emotional expression is completely ignored, and there is a great loss of information

Images