基于分块2DPCA的人脸表情识别

本文使用了分块二维主成份分析法（分块2DPCA）和模糊积分分类器进行了人脸表情识别与融合。由于分块2DPCA方法先对图像矩阵进行分块，对分块得到的子图像矩阵直接进行鉴别分析。其突出的优点是提高了特征提取的速度，在特征提取时可以完全避免使用矩阵的奇异值分解，方法简便。与2DPCA相比，可以实现使用低维的鉴别特征，而保持较高的正确识别率的目的。

Facial expression recognition based on modular 2DPCA

In this paper,modular 2DPCA Multiple classifiers with fuzzy integral calculus are used in facial expression recognition.The original images were divided into modular images,then the 2DPCA methed could be directly used to sub-images obtained from the previous step.There are some advantages for modular 2DPCA:dimension reduction of discriminant festures can be done conveniently;singular value decomposition of matrix is fully avoided in the process of features extraction,so the features for recognition can be gained easily;compared to 2DPCA,the feature matrix of lower dimension can be employed,and keep the correct recognition.