基于多通道Log-Gabor小波与（2D）~2 PCALDA的人脸识别方法  

Face recognition method based on multi-channel Log-Gabor and （2D）~2 PCALDA

作　　者：火元莲[1] 

机构地区：[1]西北师范大学物理与电子工程学院,兰州730070

出　　处：《计算机应用》2010年第11期2970-2973,共4页journal of Computer Applications

摘　　要：为了降低光照变化对基于子空间的人脸识别方法性能的影响,结合多通道Log-Gabor策略与(2D)2 PCALDA特征提取方法,提出了一种新的人脸识别方法。将不同尺度与方向作为独立通道,在每个通道内采用(2D)2 PCALDA对人脸图像的Log-Gabor表示进行特征提取、分类,然后对各通道分类结果进行决策融合得到最终的类别归属。在CAS-PEAL-R1、ORL与Yale人脸数据库上的实验结果表明,该算法具有较好的识别性能。To reduce the influence resulting from lighting variations on the performance of face recognition methods based on images, a new face recognition method, which combined the multi-channel strategy with （2D）2PCALDA feature extraction technique, was proposed. Different scale and orientation as an independent channel, the features were extracted using （2D）2PCALDA and classification was performed in each channel, and the final classification could be obtained by fusing different channel classification results. The experimental results in the CAS-PEAL-R1, ORL and Yale face database show that the proposed method has better recognition performance.

关 键 词：多通道Log-Gabor 主成分分析 线性判别式分析 (2D)2 PCALDA 人脸识别 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]