Method for recognizing facial expression based on 2D partial least square method

Abstract

A method for identifying expression of face based on 2-D bias least square method includes dividing a training sample pattern to be seven types of expressions and dividing them to be a numbers of sub-blocks in equal size, picking up vein character of each sub-block by utilizing LBP operator to form character matrix of partial vein, carrying out character pick-up on partial vein character matrix by 2-D bias least square method to form seven types of expression template data for finalizing train process and using the most close face as expression attribution of inputted image.

Description

technical field [0001] The invention relates to a facial expression recognition method, in particular to an image local feature extraction method based on a two-dimensional partial least square method. Background technique [0002] The Local Binary Pattern (LBP) operator is a rectangular block with a fixed size of 3×3, corresponding to 9 gray values. Compare the 8 surrounding gray values ​​with the central gray value, the sub-block greater than or equal to the central gray value is represented by 1, otherwise it is represented by 0, according to the 8 binary values ​​read in the clockwise direction as the 3× 3 The eigenvalue of the rectangular block, the final encoded value is the LBP value at this point. This operator can measure and extract the texture information of the local adjacent area in the grayscale image. Therefore, the LBP operator has been widely used in texture classification, image retrieval, face image analysis and other fields. [0003] Traditional facial...

AI Technical Summary

Problems solved by technology

However, the most prominent problem of this type of algorithm is that the training of AdaBoost algorithm is extremely time-consuming, and it takes at least a few days or even weeks to train a robust classifier, which seriously restricts the wide application of this type of method.

Images