Emotion recognition method and apparatus

Abstract

Embodiments of the invention provide an emotion recognition method and apparatus, which is applied to the technical field of multimedia. The method comprises the steps of recognizing an appearance characteristic of a human face in a frame sequence of a to-be-recognized video and a time characteristic of the frame sequence through a pre-built recurrent neural network model to obtain a first emotion result; recognizing the appearance characteristic of the human face in the frame sequence of the to-be-recognized video and the time characteristic of the frame sequence through a pre-built three-dimensional convolutional neural network model to obtain a second emotion result; performing fusion calculation on the first emotion result and the second emotion result to obtain a fusion result of the to-be-recognized video; and according to a maximum value in the fusion result, obtaining an emotion type of the to-be-recognized video through a pre-established corresponding relationship between the fusion result and the emotion type. According to the method and the apparatus, the complementarity of the recurrent neural network model and the three-dimensional convolutional neural network model improves the accuracy of recognizing the emotion type of the video.

Description

technical field [0001] The invention relates to the field of multimedia technology, in particular to an emotion recognition method and device. Background technique [0002] With the rapid development of artificial intelligence technology, emotion recognition can judge the emotions of characters through pictures and sounds, allowing machines to truly "understand" users, which will greatly promote the development of intelligent fields such as video understanding and human-computer interaction. Emotion recognition is a combination of technologies in multiple fields such as video screen emotion and audio emotion recognition. Video screen emotion recognition uses artificial intelligence algorithms to identify the emotions of characters through information such as facial expressions, actions, and postures in the video screen. Audio emotion recognition is mainly based on the non-stationary characteristics of human speech signals under different emotions, and judges emotional chang...

AI Technical Summary

Problems solved by technology

At present, due to the small amount of data with emotional annotations, the accuracy of RNN emotion recognition, especially the recognition of certain types of emotions (such as nausea, surprise) is low

Images