A human face emotion analysis method and system based on multi-task learning and deep learning

Abstract

The invention provides a human face emotion analysis method and system based on multi-task learning and deep learning. The method comprises the steps of learning preset analysis task convolution layers in a human face database by using a convolutional neural network to obtain a human face analysis model; acquiring a to-be-analyzed human face image, analyzing the to-be-analyzed human face image by using a human face detection algorithm and extracting human face areas in the to-be-analyzed human face image; performing prediction on the to-be-analyzed human face image by using the human face analysis model and obtaining emotion information corresponding to each human face area in the to-be-analyzed human face image. According to the invention, the concept of multi-task learning is applied to a convolutional neural network and multiple kinds of analysis tasks related to human faces can be identified by using the same analysis model, so that the size of an analysis model is reduced and identification is accelerated; different parts of a human face are described by using different convolution layers, so that each convolution layer focuses on one single task and a better identification effect can be achieved.

Description

technical field [0001] The invention belongs to the technical field of computer vision and human-computer interaction image processing, and specifically relates to a face emotion analysis method based on multi-task learning and deep learning. Background technique [0002] With the development of computer vision technology, more and more related technologies have been applied in the context of human-computer interaction in recent years, especially emotional computing. Through the automatic facial emotion recognition system, people's emotions can be understood more easily, so that people can quickly and directly obtain user emotional feedback through computers, thereby improving the quality of human-computer interaction. [0003] In the existing facial emotion recognition system, the common method is to extract low-level feature values ​​from the facial image after capturing the facial image, and then use machine learning to train a classifier for emotional classification (suc...

AI Technical Summary

Problems solved by technology

Although the face action unit and emotional space have been widely used in the task of face emotion recognition, and can achieve good results, each still has some limitations.

Images