Expression recognition method and device, electronic equipment and storage medium

Abstract

The invention provides an expression recognition method and device, electronic equipment and a storage medium, and relates to the technical field of image processing. The method comprises the following steps: acquiring a to-be-recognized face image; in the N recognition models arranged in sequence, inputting the face image into the ith recognition model for expression recognition, outputting a first recognition result, i is an integer ranging from 1 to N-1, and the initial value of i is 1; when the first recognition result is the same as the target expression type corresponding to the ith recognition model, taking the first recognition result as an actual expression recognition result and outputting the actual expression recognition result, otherwise, inputting the face image into the (i +1) th recognition model for expression recognition; and when the face image is input into the Nth recognition model, the Nth recognition model performs expression recognition on the face image and outputs a second recognition result, the second recognition result is used as an actual expression recognition result, and the Nth recognition model is configured to recognize multiple target expressiontypes. According to the method, the accuracy of facial image expression recognition can be improved.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular, to an expression recognition method, an expression recognition device, electronic equipment, and a computer-readable storage medium. Background technique [0002] Expression recognition is a research hotspot in the field of pattern recognition, and it is also a difficult point in this field. Due to the complexity of human facial expressions, the accuracy of using machine learning methods to classify expressions is low. The development of deep learning provides more possibilities for the performance improvement of image pattern recognition, so the research on expression recognition based on deep learning technology is also a popular research in the field of facial feature recognition in recent years. However, the accuracy of the current expression recognition method based on deep learning is still low. [0003] It should be noted that the information disclose...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present disclosure is to provide an expression recognition method, an expression recognition device, an electronic device, and a computer-readable storage medium, so as to overcome to a certain extent the relatively low accuracy of facial image expression recognition caused by the limitations and defects of related technologies. low problem

Images