人脸识别中的“误配准灾难”问题研究“Curse-of-Mis-alignment”-Problem.pdf

28 5 vol.28 No.5 2005 5 CHINESE JOURNAL OF COMPUTERS May 2005 1.1,2,3 -92x112 5 5 1 Tangent Distance 4-5 (a)(b)(c)1 a b c 1 2 3 E-Fisherface -Fisherface 2 3 4 5 Fisherface FERET 6 2.Fisherface 5 Fisherface 6 28 5 vol.28 No.5 2005 5 CHINESE JOURNAL OF COMPUTERS May 2005 3D Tx,Ty s q 4(Appearance)4 2.2 Fisherface FERET-FB 5 0%10%20%30%40%50%60%70%80%90%100%-4-3-2-1012340%10%20%30%40%50%60%70%80%90%100%-4-3-2-101234(a)(b)0%10%20%30%40%50%60%70%80%90%100%-16.5-12.5-8.4-4.2 04.2 8.4 12.516.50%10%20%30%40%50%60%70%80%90%100%0.7 0.780.850.93 11.071.151.22 1.3(c)(d)5 FERET-FB Fisherface 5(a)5(b)5(c)5(d)Fisherface 10 4.2 1 20 0.07 1 30 28 5 vol.28 No.5 2005 5 CHINESE JOURNAL OF COMPUTERS May 2005 Gabor Gaussian Derivatives Gabor 13 High-Order AutocorrelationHOA 14 3 15,16,17 Martinez(Perturbation)16-Gallery -4 Tangent Distance 4,18 OCR-(Robust Correlation)19(Global Affine Transform,GAT)20 3.A B 7 A 92%B 100%C A 10 B A 21 28 5 vol.28 No.5 2005 5 CHINESE JOURNAL OF COMPUTERS May 2005 2 A B C r0(%)r*(%)R S A 92 82.3 0.895 1.12 B 100 79.5 0.795 1.26 C 82 72.3 0.895 1.12 4.E-Fisherface Fisherface E-Fisherface LDA LDA/Fisherface 1 PCA Fisherface PCA PCA -Wpca 2 LDA 88LDA 9 81 81 9 PCA Wpca LDA Wlda 3 WpcaWlda Fisherface Gallery LDA LDAGalleryLDA 8 8 E-Fisherface Martinez(Perturbation)16Martinez Gallery -Gallery 28 5 vol.28 No.5 2005 5 CHINESE JOURNAL OF COMPUTERS May 2005 9 5.FERET-FB CAS-PEAL-R1 5.1 FERET FERET FB 2.1 10 E-Fisherface Fisherface 3/28 10 Fisherface E-Fisherface 3 E-Fisherface Fisherface E-Fisherface 0%10%20%30%40%50%60%70%80%90%100%-4-3-2-101234FisherfaceE-Fisherface 0%10%20%30%40%50%60%70%80%90%100%-4-3-2-101234FisherfaceE-Fisherface(a)(b)0%10%20%30%40%50%60%70%80%90%100%-16.5-12.5-8.4-4.204.28.412.5 16.5FisherfaceE-Fisherface 0%10%20%30%40%50%60%70%80%90%100%0.72 0.79 0.86 0.93 11.07 1.14 1.21 1.28FisherfaceE-Fisherface(c)(d)28 5 vol.28 No.5 2005 5 CHINESE JOURNAL OF COMPUTERS May 2005 Fisherface 5.3 6.Fisherface Fisherface E-Fisherface FERET 1.Fisherface Fisherface 2.3.Fisherface E-Fisherface -Fisherface Gabor 1 Chellappa R.,Wilson C.L.,Sirohey S.,Human and machine recognition of faces:a survey,Proceedings of the IEEE,1995,83(5):705-740 2 Phillips P.J.,Moon H.,etc.“The FERET evaluation methodology for face-recognition algorithms,”IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(10):1090-1104 3 Philips P.J.,Grother P.J.,Micheals R.J.,Blackburn D.M.,E.Tabassi,and J.M.Bone,Face Recognition Vendor Test 2002:evaluation report,Technical Report,NISTIR 6965,National Institute of Standards and Technology,2003(http:/www.frvt.org)4 Simard P.Y.,LeCun Y.A.,Denker J.S.,and Victorri B,Transformation invariance in pattern recognition-tangent distance and tangent propagation.International Journal of Imaging System and Technology,2001,11(3):181-194 5 P.N.Belhumeur,J.P.Hespanha etc.Eigenfaces vs Fisherfaces:recognition using class specific linear projection,1997,IEEE Transactions on Pattern Analysis and Machine Intelligence,20(7):711-720 6 Shan S.,Chang Y.,Gao W.,Cao B.,Curse of mis-alignment in face recognition:problem and a novel mis-alignment learning solution,in Proceeding of The 6th International Conference on Face and Gesture Recognition,Jeju,Korea,2004,314-320 7 Buhman J.,Lades M.,and Malsburg C.von der,Size and distortion invariant object recognition by hierarchical graph matching,in Proc.of IEEE International Joint Conference on Neural Network,San Diego,CA,Jan.1989,vol.2:411-416.8 Lades M.,Vorbruggen J.C.,etc,Distortion invariant object recognition in the dynamic link architecture,IEEE Trans.On Computers,1993,42(3):300-311 9 Wiskott L,Fellous J.M,Kruger N.,Malsburg C.von der,Face recogniton by elastic bunch graph matching,IEEE Transactions on Pattern Analysis and Machine Intelligence,1997,19(7):775-779 28 5 vol.28 No.5 2005 5 CHINESE JOURNAL OF COMPUTERS May 2005 SHAN Shiguang,male,born in March 1975,Ph.D.,Assistant Researcher in Institute of Computing Technology,Chinese Academy of Sciences.His research interests include pattern analysis,machine learning,and computer vision.He is especially absorbed in face recognition related research topics.GAO Wen,male,born in 1956,Ph.D.,Professor in Institute of Computing Technology and Graduated School of Chinese Academy of Sciences.He is also a professor in Harbin Institute of Technology.His research interests include multimedia data compression,image processing,computer vision,multimodal interface,artificial intelligence and virtual reality.CHANG Yizheng,female,born in 1979,Master candidate in School of Computer,Harbin Institute of Technology.Her research is focused on face recognition.CAO Bo,male,born in 1977,Ph.D Candidate in Institute of Computing Technology,Chinese Academy of Sciences.He is currently working on face recognition.CHEN Xilin,male,born in 1965,Ph.D.,Professor in Institute of Computing Technology,Chinese Academy of Sciences and School of Computer,Harbin Institute of Technology.His research interests include computer vision,pattern recognition,machine learning,and intelligent human-computer interface.010-58858300-314 Email: Background of the article:This work is conducted in the ICT-ISVISION Joint R&D Lab for face recognition(hereinafter named by FRJDL),Institute of Computing Technology Chinese Academy of Sciences,which has been working on face recognition related researches for more than 9 years as the first specialized lab on face recognition in China.FRJDL has always been aiming at inventing fully innovative kernel technologies and dealing with key issues in Biometrics,especially in face recognition area,based on which,multiple disciplines such as pattern recognition,machine learning,and computer vision,are theoretically studied.In the last 9 years,plenty of research work has been done on the basic theories in face recognition,as well as the practical engineering techniques.About 100 research papers had been published by the FRJDL members.And many of our research fruits have been successfully applied to practical applications such as bank surveillance,access control,and time-card systems.The work presented in this paper is just motivated by one of our practical fully automatic face recognition systems.In the system,we noticed that a large percent of false identification events are caused actually by the inaccurate eye localization results.To improve the robustness of the system to this kind of errors,we have conducted the work presented in this paper.