Computer Engineering and Applications ›› 2014, Vol. 50 ›› Issue (2): 175-178.

Previous Articles     Next Articles

Combination of improved modular 2DPCA and maximum scatter difference discriminate analysis for face recognition

KONG Aixiang, WANG Chengru   

  1. School of Computer Science and Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China
  • Online:2014-01-15 Published:2014-01-26

改进的模块2DPCA与MSD结合的人脸识别

孔爱祥,王成儒   

  1. 燕山大学 信息科学与工程学院,河北 秦皇岛 066004

Abstract: A method of combination of improved modular 2DPCA and Maximum Scatter Difference discriminate analysis(MSD) is proposed. The improved modular 2DPCA is applied to the original face images for feature extraction. Then MSD is used to the sub-images of these obtained feature images in which way the final feature images are obtained. This method can not only exploit local features of original image and discriminate information but also totally avoid the problem of singular value decomposition of matrix. Experiments performed on ORL face database verify the effectiveness of the proposed method.

Key words: modular 2 Dimensional Principal Component Analysis(2DPCA), maximum scatter difference discriminate analysis, face recognition

摘要: 提出了一种改进的模块2DPCA与最大散度差鉴别分析相结合的人脸识别方法。该方法先对原始人脸图像采用改进的模块2DPCA抽取特征,然后对得到的特征图像的子图像块施行最大散度差鉴别分析,得到最终的特征图像。该方法不仅利用了原始图像的局部特征和类别信息,而且完全避免了使用矩阵的奇异值分解。在ORL人脸库上的实验结果验证了该方法的有效性。

关键词: 模块二维主成分分析(2DPCA), 最大散度差鉴别分析, 人脸识别