Facial expression recognition method based on improved elastic module matching algorithm

Abstract

The invention discloses a facial expression recognition method based on an improved elastic module matching algorithm, and the method comprises the steps: training an expression image data set by a non-uniform grid to acquire an expression feature data set for the feature information of expression change key points; and determining the mode corresponding to the template feature map of the minimumcost function as the mode category of a to-be-identified image by solving the minimum cost function of the template feature map in the expression feature data set and the to-be-identified image. By training the expression image data set as the standard, the features are extracted to form the template feature graph, the subsequent recognition calculation amount can be reduced, and the cost functioncalculation with the to-be-identified object is performed based on the template feature graph, so that the recognition accuracy is improved. In the process, the minimum cost function of the templatefeature map and the to-be-identified image is obtained through the elastic grid, so that the type of the recognized facial expression is determined, the case can be effectively defined, the expressionrecognition rate is greatly improved, and the operation time can be effectively shortened.

Description

Technical field[0001]This application relates to the field of image processing technology, and in particular to a facial expression recognition method based on an improved elastic module matching algorithm.Background technique[0002]Facial expression recognition technology has become a hot development technology in recent years with the rapid development of some related fields such as machine learning, image processing, and human recognition. The influence and potential of the facial expression recognition system are simultaneously extended to a wide range of applications, such as human-computer interaction, intelligent robots, driver status monitoring and so on. The facial expression recognition system is a prerequisite for computers to understand people's emotions, and it is also an effective way for people to explore and understand intelligence. How to realize the personification of the computer so that it can adaptively provide the most friendly operating environment for the comm...

AI Technical Summary

Problems solved by technology

The traditional elastic template matching algorithm uses a uniform grid to extract the feature information of the whole face and then uses the nearest neighbor classification strategy for matching and recognition, which introduces interference from parts that contribute less to expression changes, such as facial contours, forehead, and cheeks. Information, the amount of calculation is doubled, and the recognition rate is reduced

Images