Expression recognition method and system

Abstract

The embodiment of the invention discloses an expression recognition method. The expression recognition method comprises the steps that a face image to be recognized is input to a global depth convolution nerve network to determine a first expression and a first value of the face image, wherein the global depth convolution nerve network is obtained by deep learning a reference face image with different expressions; the face image is partitioned into multiple sub-images; feature information of the sub-images is compared with reference feature information to determine a second expression and a second value of the face image, wherein the reference feature information is determined by multiple reference sub-images of the reference face image with the different expressions; the expression of the face image is determined according to the first expression, the first value, the second expression and the second value. Correspondingly, the invention further provides an expression recognition system. According to the method and system, the face expression can be more accurately and more quickly recognized.

Description

Technical field [0001] The present invention relates to the technical field of image recognition, in particular to an expression recognition method and system. Background technique [0002] Image-based facial expression recognition has important value in human-computer interaction, human emotion judgment and other intelligent fields. [0003] The method for recognizing facial expressions in the prior art is limited to facial expression recognition on clear and still pictures, and in order to accurately complete facial expression recognition, the recognized picture needs to be a frontal image of a human face. If the picture to be recognized is in In the process of human activities, it is very likely that the pictures obtained are virtual, unclear, or the quality of the pictures obtained is difficult to distinguish due to factors such as ambient light, and the pictures captured are likely to be only the profile of the person. The non-frontal image can not accurately recognize the fa...

AI Technical Summary

Problems solved by technology

[0003] The methods for recognizing facial expressions in the prior art are limited to expressive recognition on clear still pictures, and in order to accurately complete expression recognition, the recognized picture needs to be a frontal image of a human face. If the picture to be recognized is in If you take pictures while people are in motion, it is very likely that the pictures you get will be blurry, unclear, or due to factors such as ambient light, the quality of the pictures you get is difficult to distinguish, and the pictures you get are likely to be just people's profile faces. Non-frontal face images, at this time, people's facial expressions cannot be accurately recognized, which seriously affects the application of facial expression recognition in real life

Images