基于核典型相关分析的多特征组合人脸识别

为了提高人脸的识别率，利用多特征和分类器之间的互补优势，提出一种基于核典型相关分析的多特征组合人脸识别方法（KCCA-MF）。提取人脸图像的LBP特征和Gabor特征，采用核典型相关分析算法对两种特征进行融合，以消除冗余特征，采用K近邻算法和支持向量机建立组合人脸分类器，并采用3个经典人脸库进行仿真分析。结果表明，相对于其他人脸识别方法，KCCA-MF提高了人脸识别的识别准确率和效率，可以满足人脸识别的实时性要求。

Face recognition based on hybrid features fusion by kernel canonical correlation analysis

In order to improve the recognition rate of face image, a novel face recognition method （KCCA-MF） is proposed based on hybrid features fusion by kernel canonical correlation analysis. Gabor and LBP features of face images are extracted, and then the kernel correlation analysis algorithm is used to fuse two kinds of features and eliminate redundant features, the combination of face image classifier is established based on K nearest neighbor and support vector machine, and the simulation analysis is carried on three classic face databases. The results show that, compared with other face recognition methods, the proposed method improves the recognition accuracy, and can meet the real-time requirements of face recognition.