Facial expression recognizing method based on Gabor transform optimal channel blur fusion

Abstract

The invention provides a facial expression recognizing method based on Gabor transform optimal channel blur fusion, comprising the following steps of: S1, dividing a Gabor filter into 11 channels, carrying out Gabor wavelet transform on a facial expression image subjected to normalization by the Gabor filter to extract texture characteristics of the facial expression image; S2, establishing classifiers corresponding to the channels one by one, respectively sending the texture characteristics extracted from the channels into the classifiers for classifying and recognizing, calculating the recognition rate and the definition of each classifier to various expressions, selecting 4 classifiers with top comprehensive ranking of the recognition rate and the definition to be used as optimal classifiers; and S3, carrying blur fusion on the four optimal classifiers to obtain a facial expression recognition result. The facial expression recognition method has the advantages of small calculated amount, high calculating speed and high recognition precision.

Description

technical field [0001] The present invention relates to a kind of pattern recognition method, specifically, it is a kind of facial expression recognition method based on Gabor (transliteration: Gabor) transformation optimal channel fuzzy fusion for machine automatic recognition of human facial expression in computer vision research . Background technique [0002] Using computer technology to realize automatic recognition of human facial expressions is a hot issue in computer pattern recognition research. In a facial expression recognition system, the extraction of facial expression features and the setting of classifiers are the two most critical technologies. Since there are many factors that affect the performance of facial expression recognition, such as environment, illumination, age, posture, image resolution and imaging noise, etc., will have a certain impact on the results of face recognition, so the current feature extraction algorithm has made some progress. , but...

AI Technical Summary

Problems solved by technology

Since there are many factors that affect the performance of facial expression recognition, such as environment, illumination, age, posture, image resolution and imaging noise, etc., will have a certain impact on the results of face recognition, so the current feature extraction algorithm has made some progress. , but not yet mature and perfect

At the same time, since the classification of facial expressions is a very complicated problem, how to select the classifier with the best performance is also an important topic in the research of pattern recognition.

[0003] A method for extracting facial expression features using Gabor wavelets is disclosed in the patent application "Face Recognition Method and Device for Fusion of Face Component Features and Gabor Face Features" (patent application number is 200810104401.6). Performing Gabor wavelet transform on the facial expression image and then performing PCA (principal component analysis, principal component analysis) on the Gabor feature image has a relatively high recognition rate, but its calculation amount is relatively large, and there is still room for further improvement in the recognition accuracy

Images