[1]谢红,宁志刚,张磊.基于DCT和2D-PCA的人脸识别算法研究[J].应用科技,2009,36(06):34-37.[doi:doi:10.3969/j.issn.1009-671X.2009.06.008]
 XIE Hong,NING Zhi-gang,ZHANG Lei.Face recognition system based on DCT and modular 2DPCA[J].yykj,2009,36(06):34-37.[doi:doi:10.3969/j.issn.1009-671X.2009.06.008]
点击复制

基于DCT和2D-PCA的人脸识别算法研究
分享到:

《应用科技》[ISSN:1009-671X/CN:23-1191/U]

卷:
第36卷
期数:
2009年06期
页码:
34-37
栏目:
计算机技术与应用
出版日期:
2009-06-05

文章信息/Info

Title:
Face recognition system based on DCT and modular 2DPCA
文章编号:
1009-671X(2009)06-0034-04
作者:
谢红宁志刚张磊
哈尔滨工程大学 信息与通信工程学院,黑龙江哈尔滨 150001
Author(s):
XIE Hong NING Zhi-gangZHANG Lei
College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China
关键词:
离散余弦变换模块二维主元分析图像重建人脸识别
Keywords:
DCT 2DPCA image reconstruction face recognition
分类号:
TP391.41
DOI:
doi:10.3969/j.issn.1009-671X.2009.06.008
文献标志码:
A
摘要:
提出了一种对角DCT和模块2DPCA相结合的人脸识别方法.该算法首先将人脸图像转换成对角图像,提取人脸的行、列与结构信息以求解最优识别向量.然后利用DCT压缩以去掉人眼不敏感的中频分量与高频分量,再由IDCT重建人脸图像,这样有限降低了所需特征的维数,减少了计算量.然后通过模块2DPCA进行特征提取得到人脸识别特征,最后运用最近邻分类器完成人脸的识别.基于ORL及Yale人脸数据库的实验结果证明了该算法的有效性与稳健性.
Abstract:
A face recognition method based on the combination of discrete cosine transform (DCT) and modular twodimensional principal component analysis(2DPCA) was put forward. Firstly a face image was turned into a diagonal image which contains the row, column and structure information to the solve optimal recognition vector. Secondly the image was processed by DCT and IDCT to reduce the character dimensions effectively. Thirdly, the image was processed by 2DPCA to obtain the face recognition characters. Finally, the nearest neighbor (NN) classifier was selected to perform face recognition. The experimental results of Yale face database which are based on ORL show that this method is efficient in the face recognition.

参考文献/References:

[1]FMATOS F M de S S, BATISTA L V,POEL J D. Face recognition using DCT coefficients selection[C]//Proceedings of the 2008 ACM Symposium on Applied Computing. Fortaleza:Brazl, 2008:1753-1757.
[2] BELHUMEUR P,HESPANHA J,KRIEGMAN D. Eigenfaces vs fisherfaces:recognition using class specific linear projection\[J\].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):71-72.
[3]甘俊英, 高建虎, 李春芝.基于2D-DCT和模块2D-PCA的人脸识别系统的实现[J]. 计算机工程应用,2007,43(31):210-213.
[4] 陈伏兵, 陈秀宏, 张生亮,等.基于模块2DPCA的人脸识别方法\[J\]. 中国图像图形学报,2006,11(4):580-585.
[5]山世光.人脸识别中若干关键问题研究[D].北京: 中科院计算所, 2004.

备注/Memo

备注/Memo:
作者简介:谢红(1962-),女,教授,主要研究方向:通信与信息系统,E-mail:xiehong@hrbeu.edu.cn.
更新日期/Last Update: 2009-06-24