[1]范燕,於东军,宋晓宁,等.镜像基函数下过渡投影子空间人脸特征抽取算法[J].南京理工大学学报(自然科学版),2012,36(06):0.
 FAN Yan,YU Dong jun,SONG Xiao ning,et al.Face Feature Extraction Approach of Projective Transition Subspace Based on Basis Function of Mirror Symmetry[J].Journal of Nanjing University of Science and Technology,2012,36(06):0.
点击复制

镜像基函数下过渡投影子空间人脸特征抽取算法
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
36卷
期数:
2012年06期
页码:
0
栏目:
出版日期:
2012-12-31

文章信息/Info

Title:
Face Feature Extraction Approach of Projective Transition Subspace Based on Basis Function of Mirror Symmetry
作者:
范燕 1於东军 2宋晓宁 1束鑫1
1.江苏科技大学 计算机科学与工程学院,江苏 镇江 212003; 2.南京理工大学 计算机科学与工程学院,江苏 南京 210094
Author(s):
FAN Yan1YU Dongjun2SONG Xiaoning1SHU Xin1
1.School of Computer Science and Engineering,Jiangsu University of Science and Technology, Zhenjiang 212003,China;2.School of Computer Science and Engineering,NUST,Nanjing 210094,China
关键词:
镜像基函数过渡矩阵人脸识别小样本问题
Keywords:
basis function of mirror symmetrytransition matrixface recognitionsmall sample size problem
分类号:
TP391.41
摘要:
为强化鉴别信息的完整性,提升解决小样本问题(SSSP)的能力,该文构造了一种求解具有几何对称性的样本鉴别信息的特征抽取算法。从线性子空间的角度出发,利用人脸的几何对称性,依据奇偶分解原理,在原特征空间生成一组镜像对称基函数。构造一种矩阵变换,求出两个对称基之间的过渡矩阵,并在过渡矩阵空间上求取最优鉴别矢量集。该方法强化了鉴别信息的完整性,对解决SSSP是有效的。在ORL和FERET人脸数据库上的实验结果验证了算法的有效性。
Abstract:
To enhance the integrity of discrimination information and improve the ability of solving small sample size problems(SSSP),a feature extraction approach is constructed to solve the sample identification information with geometric symmetry.From the view of linear subspace,a set of mirror symmetrical basis functions are constructed in original space according to the geometric symmetry of face images and the oddeven decomposition theorem.A matrix transform is presented to obtain the transition matrix between the two oddeven basis functions.The optimal discrimination vectors are obtained in the transition matrix space.This method enhances the integrity of discrimination information and solves the SSSP effectively.Experimental results from the ORL and FERET face image databases demonstrate the effectiveness of the proposed method.

参考文献/References:

[1]FukunagaK.Introduction to statistical pattern recognition[M].2nd ed.New York,USA:Academic Press,1990. 
[2]SongXiaoning,Zheng Yujie,Wu Xiaojun,et al.A complete fuzzy discriminant analysis approach for face recognition[J].Applied Soft Computing,2010,15(10):208-214. 
[3]SongXiaoning,Yang Xibei,Zheng Yujie,et al.Discriminant analysis approach using fuzzy fourfold subspaces model[J].Neurocomputing,2010,73(10):2255-2265. 
[4]Marcel S.A symmetric transformation for LDAbased face verification[A].Proceedings of the 6th International Conference on Automatic Face and Gesture Recognition[C].New York,USA:IEEE,2004,207-212.
[5]严云洋,郭志波,陈伏兵,等.融合多尺度多特征的人〖JP〗脸识别方法[J].南京理工大学学报,2009,33(1):47-52. 
[6]Laboratories Cambridge.ORL face database[EB/OL].http://www.camorl.co.uk/facedatabase.htm,2009-02-14. 
[7]PhillipsP J,Moon H,Rizvi S A,et al.The FERET evaluation methodology for facerecognition algorithms[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(10):1090-1104. 
[8]BelhumeurP N,Hespanha J P,Kriegman D J,et al.Fisherfaces:Recognition using class specific linear projection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):711-720. 
[9]YuH,Yang J.A direct LDA algorithm for highdimensional data—with application to face recognition[J].Pattern Recognition,2001,34(11):2067-2070. 
[10]YangJ,Frangi A F,Yang J Y,et al.KPCA plus LDA:A complete kernel Fisher discriminant framework for feature extraction and recognition[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(2):230-244.

备注/Memo

备注/Memo:
收稿日期:2011-11-11修回日期:2012-10-12 基金项目:中国博士后科学基金(2011M500926);江苏省自然科学基金(BK2012700;BK2011371);江苏省博士后科学基金(1102063C);人工智能四川省重点实验室开放基金重点项目(2012RZY02) 作者简介:范燕(1978-),女,硕士,讲师,主要研究方向:模式识别与智能系统、图像处理,Email:ecsi_fy@yahoo.com.cn;通讯作者:於东军(1975-),男,博士,副教授,主要研究方向:模式识别与智能信息处理,生物信息学,Email:njyudj@.njust.edu.cn。
更新日期/Last Update: 2012-12-29