基于二维最大边缘准则和DCT的人脸识别方法  

Two-dimensional maximum margin criterion in DCT domain for face recognition

作　　者：张玉华[1,2] 王欣[2] 

机构地区：[1]山东大学医学院,山东济南250012 [2]山东大学信息科学与工程学院,山东济南250100

出　　处：《光电子．激光》2009年第10期1361-1364,共4页Journal of Optoelectronics·Laser

基　　金：国家自然科学基金资助项目(60872119)

摘　　要：提出了一种基于离散余弦变换(DCT)和二维最大边缘准则(2DMMC)的2DDM特征提取算法,证明了2DMMC可以直接应用于DCT域,利用欧氏距离测度进行分类的结果与在空域中进行得到的结果完全相同。2DMMC方法可直接应用于基于DCT压缩的JPEG格式的图像。在ORL和Yale人脸数据库上的实验结果表明,在空域2DMMC的识别率高于2DPCA和2DLDA,2DDM的识别率又高于2DMMC,而且2DDM的耗时要低于2DMMC。A new feature extraction method called as 2DDM is proposed based on discrete cosine transform(DCT) and two-dimensional maximum margin criterion(2DMMC).It is also proven that the 2DMMC can be directly implemented in the DCT domain and the classification results by the measure of Euclidean distance are exactly the same as the one obtained from the spatial domain.For images compressed using the DCT,2DMMC can be directly implemented so that the inverse DCT(IDCT) can be skipped and the computational cost is redu...

关 键 词：人脸识别 特征抽取 离散余弦变换(DCT) 二维最大边缘准则(2DMMC) 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]