基于单演同相幅值模式的人脸识别方法.pdfVIP

132 2014 ，50（18） Computer Engineering and Applications 计算机工程与应用 ⦾图形图像处理⦾ 基于单演同相幅值模式的人脸识别方法 刘机福，王炼红，汤春龙 LIU Jifu, WANG Lianhong, TANG Chunlong 湖南大学 电气与信息工程学院，长沙 410082 College of Electrical and Information Engineering, Hunan University, Changsha 410082, China LIU Jifu, WANG Lianhong, TANG Chunlong. Face recognition algorithm based on pattern of monogenic magni- tudes with same phase. Computer Engineering and Applications, 2014, 50 （18）：132-136. Abstract ：In order to take advantages of the monogenic magnitude and phase information for face recognition, a new method based on pattern of monogenic magnitudes with same phase is proposed. Multi-scale monogenic filters are used to extract the monogenic magnitude and phase information of the image. This paper obtains the phase quantization images, accumu- lates the magnitude according to the quantization results and codes the accumulative results by binary strategy. After that the patterns of monogenic magnitudes with same phase image are obtained. PMMSP maps are divided into blocks and the histo- gram is extracted from the blocks. BFLD is not only used to reduce the dimension of the features but also enhance its discrimi- native power. The experimental results on the CAS-PEAL and AR face databases show that the proposed algorithm is effective. Key words ：face recognition; monogenic filter; phase; Pattern of Monogenic Magnitudes with Same Phase （PMMSP ）; Block-based Fisher Linear Discriminant （BFLD ） 摘 要：针对单演信号表述仅利用幅值和方向而忽略相位信息的问题，提出了一种单演同相幅值模式方法。用多尺 度的单演滤波器提取人脸的单演幅值和相位信息，将相位量化并根据相位量化的结果对幅值累加和二值编码，从而 获得若干张单演同相幅值模式图。将每一张PMMSP 图分块并提取直方图特征，用BFLD 对特征进行降维。这样能 有效提升特征的判别能力并降低算法的时间和空间复杂度。在CAS-PEAL 人脸库和AR 人脸库上的实验证明了该 算法的有效性。 关键词：人脸识别；单演滤波；相位；单演同相幅值模式；分块线性判别 文献标志码：A 中图分类号：TP391.41 doi ：10.3778/j.issn. 1002-8331.1311-0134 1 引言 像的单演幅度和方向信息进行人脸识别并获得了极好 近年来，人脸识别逐渐成为模式识别和计算机视觉 的效果。实验表明基于单演滤波的方法的识别性能与 领