Human facial dynamic expression recognition method and device based on artificial neural network

Abstract

The present application provides a method and device for recognizing facial dynamic expressions based on an artificial neural network. The method is applied to the prediction of the identity and / or expression intensity category of a person's expression in a video in a scene where the person is fixed; the method includes: Obtain the original video data of the person to be tested, and determine the image data of the preset frame number in the original video data; generate a feature group according to the image data of the preset frame number; use the self-learning ability of artificial intelligence to establish the The corresponding relationship between the feature group of the person to be tested and the dynamic expression classification of the person to be tested; the current feature group of the current person to be tested is obtained; through the corresponding relationship, determine the current dynamic corresponding to the current feature group Expression classification. By analyzing the facial dynamic expression video in a fixed scene, the identity and expression intensity category of the expression can be predicted, so it can be mainly applied to fixed scenes such as units, factories, classrooms, etc.

Description

technical field [0001] The present application relates to the field of facial expression detection, in particular to a method and device for recognizing dynamic facial expressions by an artificial neural network. Background technique [0002] With the development of science and technology, the field of face recognition is becoming wider and wider. From the face-swiping check-in in daily life to the popularization of face-swiping payment, face recognition has always been a research hotspot in the field of computer vision and pattern recognition. In addition to verification, it also has a wide range of applications in the fields of video surveillance and network retrieval. With the development of deep learning and the improvement of computer computing performance, face recognition technology has made significant progress in recent research, and achieved quite good recognition rates on multiple data sets. How to use the face data obtained by recognition has also become the foc...

AI Technical Summary

Problems solved by technology

[0005] At present, the research on the learning of human facial expressions is extensive and high-quality, but due to the different facial structures of each person and the influence of psychological reflection differences, the application of a single expression map in practical applications is relatively limited.

Images