Learning multiview face subspaces and facial pose estimation using independent component analysis

IEEE Transactions on Image Processing

Volumn 14, Issue 6, 2005, Pages 705-712

  Li, Stan Z ^a   Lu, XiaoGuang ^b   Hou, Xinwen ^c,d   Peng, Xianhua ^c   Cheng, Qiansheng ^c  

^a MICROSOFT RESEARCH ASIA   (China)

^b Michigan State University   (United States)

^c PEKING UNIVERSITY   (China)

^d INSTITUTE OF GEOLOGY AND GEOPHYSICS   (China)

Author keywords

Appearance based approach; Face analysis; Independent component analysis (ICA); Independent subspace analysis (ISA); Learning by examples; Topographic independent component analysis (TICA); View subspaces

Indexed keywords

COLOR IMAGE PROCESSING; ESTIMATION; FEATURE EXTRACTION; IMAGE ANALYSIS; LEARNING ALGORITHMS; MATHEMATICAL MODELS; PRINCIPAL COMPONENT ANALYSIS; PROBABILITY DISTRIBUTIONS;

APPEARANCE BASED APPROACH; FACE ANALYSIS; FACE SUBSPACES ESTIMATION; FACIAL POSE ESTIMATION; INDEPENDENT SUBSPACE ANALYSIS (ISA); LEARNING BY EXAMPLES; NONLINEAR FEATURE TECHNIQUE; TOPOGRAPHIC INDEPENDENT COMPONENT ANALYSIS (TICA);

FACE RECOGNITION;

ALGORITHM; ARTICLE; ARTIFICIAL INTELLIGENCE; AUTOMATED PATTERN RECOGNITION; BIOLOGICAL MODEL; BODY POSTURE; COMPARATIVE STUDY; COMPUTER ASSISTED DIAGNOSIS; COMPUTER SIMULATION; EVALUATION; FACE; HISTOLOGY; HUMAN; IMAGE ENHANCEMENT; INFORMATION RETRIEVAL; METHODOLOGY; PHOTOGRAPHY; PHYSIOLOGY; PRINCIPAL COMPONENT ANALYSIS; REPRODUCIBILITY; SENSITIVITY AND SPECIFICITY; STATISTICAL MODEL;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; COMPUTER SIMULATION; FACE; HUMANS; IMAGE ENHANCEMENT; IMAGE INTERPRETATION, COMPUTER-ASSISTED; INFORMATION STORAGE AND RETRIEVAL; MODELS, BIOLOGICAL; MODELS, STATISTICAL; PATTERN RECOGNITION, AUTOMATED; PHOTOGRAPHY; POSTURE; PRINCIPAL COMPONENT ANALYSIS; REPRODUCIBILITY OF RESULTS; SENSITIVITY AND SPECIFICITY;

EID: 20444369119     PISSN: 10577149     EISSN: None     Source Type: Journal    
DOI: 10.1109/TIP.2005.847295     Document Type: Article

References (51)

1. A. Kuchinsky, C. Pering, M. L. Creech, D. Freeze, B. Serra, and J. Gwizdka, "Fotofile: A consumer multimedia organization and retrieval system," presented at the ACM SIG CHI Conf., Pittsburg, PA, May 1999.
2. R. Brunelli, "Estimation of pose and illuminant direction for face processing," Massachusetts Inst. Technol., Cambridge, MA, A. I. Memo 1499, 1994.
3. P.W. Hallinan, "A low-dimensional representation of human faces for arbitrary lighting conditions," in Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 1994, pp. 995-999.
4. R. Epstein, P. Hallinan, and A. Yuille, "5 ± 2 eigenimages suffice: An empirical investigation of low-dimensional lighting models," in Proc. IEEE Workshop Physics-Based Vision, 1995, pp. 108-116.
5. Y. Adini, Y. Moses, and S. Ullman, "Face recognition: The problem of compensating for changes in illumination direction," IEEE Trans. Pattern Anal. Mach. Intell., vol. 19, no. 7, pp. 721-732, Jul. 1997.
6. P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, "Eigenfaces vs. Fisherfaces: Recognition using class specific linear projection," IEEE Trans. Pattern Anal. Mach. Intell., vol. 19, no. 7, pp. 711-720, Jul. 1997.
7. K. Etemad and R. Chellapa, Face Recognition Using Discriminant Eigenvectors, 1996.
8. A. Shashua, "On photometric issues in 3d visual recognition from a single 2d image," Int. J. Comput. Vis., vol. 21, pp. 99-122, 1997.
9. S. Baker, S. Nayar, and H. Murase, "Parametric feature detection," Int. J. Comput. Vis., vol. 27, no. 1, pp. 27-50, Mar. 1998.
10. P. N. Belhumeur and D. J. Kriegman, "What is the set of images of an object under all possible illumination conditions," Int. J. Comput. Vis., vol. 28, no. 3, pp. 245-260, Jul. 1998.
11. A. S. Georghiades, D. J. Kriegman, and P. N. Belhumeur, "Illumination cones for recognition under variable lighting: Faces," in Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 1998, pp. 52-59.
12. H. F. Chen, P. N. Belhumeur, and D. W. Jacobs, "In search of illumination invariants," in Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 2000, pp. 254-261.
13. A. Yilmaz and M. Gokmen, "Eigenhill vs. eigenface and eigenedge," in Proc. Int. Conf. Pattern Recognition, Barcelona, Spain, 2000, pp. 827-830.
14. J. Hornegger, H. Niemann, and R. Risack, "Appearance-based object recognition using optimal feature transforms," Pattern Recognit., vol. 33, no. 2, pp. 209-224, Feb. 2000.
15. A. Shashua and T. R. Raviv, "The quotient image: Class based re-rendering and recognition with varying illuminations," IEEE Trans. Pattern Anal. Mach. Intell., vol. 23, no. 2, pp. 129-139, May 2001.
16. M. Bichsel and A. P. Pentland, "Human face recognition and the face image set's topology," CVGIP: Image Understanding, vol. 59, pp. 254-261, 1994.
17. H. Murase and S. K. Nayar, "Visual learning and recognition of 3-D objects from appearance," Int. J. Comput. Vis., vol. 14, pp. 5-24, 1995.
18. S. Gong, S. McKenna, and J. Collins, "An investigation into face pose distribution," presented at the IEEE Int. Conf. Face and Gesture Recognition, 1996.
19. D. Graham and N. Allinson, "Face recognition from unfamiliar views: Subspace methods and pose dependency," in Proc. 3rd Int. Conf. Automatic Face and Gesture Recognition, Nara, Japan, Apr. 1998, pp. 348-353.
20. H. Borotschnig, L. Paletta, M. Prantl, and A. Pinz, "Active aobject recognition in parametric eigenspace," in Proc. 9th Brit. Machine Vision Conf., Southampton, UK, 1998, pp. 63-72.
21. M. Kirby and L. Sirovich, "Application of the karhunen-loeve procedure for the characterization of human faces," IEEE Trans. Pattern Anal. Mach. Intell., vol. 12, no. 1, pp. 103-108, Jan. 1990.
22. M. A. Turk and A. P. Pentland, "Face recognition using eigenfaces," in Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, Jun. 1991, pp. 586-591.
23. A. Talukder and D. Casasent, "A closed-form neural network for discriminatory feature extraction from high-dimensional data," Neural Netw., vol. 14, no. 9, pp. 1201-1218, 2001.
24. A. Talukder and D. Casasent, "Pose invariant recognition of faces at unknown aspect views," presented at the Int. Joint Conf. Neural Networks (IJCNN), 1999.
25. A. Talukder and D. Casasent, "Classification and pose estimation of objects using nonlinear features," in Proc. SPIE: Applications and Science of Computational Intelligence, vol. 3390, Apr. 1998, pp. 12-23.
26. A. Khotanzad and J. J.-H. Liou, "Recognition and pose estimation of unoccluded three-dimensional objects from a two-dimensional perspective view by banks of neural networks," IEEE Trans. Neural Netw., vol. 7, no. 4, pp. 897-906, Aug. 1996.
27. C. Jutten and J. Herault, "Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture," Signal Process., vol. 24, pp. 1-10, 1991.
28. P. Comon, "Independent component analysis - A new concept?," Signal Process., vol. 36, pp. 287-314, 1994.
29. S. Z. Li, X. G. Lu, H. J. Zhang, Q. Fu, and Y. Cheng, "Learning topographic representation for multi-view object appearances," in Proc. ICASSP, vol. 2, Salt Lake City, UT, May 8-11, 2001, pp. 1329-1332.
30. S. Z. Li, X. G. Lu, and H. J. Zhang, "View based clustering of object appearances based on independent subspace analysis," in Proc. IEEE Int. Conf. Computer Vision, vol. 2, Vancouver, BC, Canada, Jul. 2001, pp. 295-300.
31. S. Z. Li, X. G. Lu, and H. J. Zhang, "View-subspace analysis of multi-view face patterns," in Proc. IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-time Systems, Vancouve, BCr, Canada, Jul. 13, 2001, pp. 125-132.
32. S. Z. Li, X. H. Peng, X. W. Hou, H. J. Zhang, and Q. S. Cheng, "Multiview face pose estimation based on supervised learning," presented at the IEEE Int. Conf. Automatic Face and Gesture Recognition, Washington, DC, May 2002.
33. A. Hyvärinen, P. Hoyer, and M. Inki, "Topographic independent component analysis," Neural Comput., vol. 13, to be published.
34. A. Hyvärinen and P. Hoyer, "Emergence of topography and complex cell properties from natural images using extensions of ica," Adv. Neural Inf. Process. Syst., vol. 12, pp. 827-833, 2000.
35. B. A. Olshausen and D. J. Field, "Natural image statistics and efficient coding," Network, vol. 7, pp. 333-339, 1996.
36. A. J. Bell and T. J. Sejnowski, "The independent components of natural scenes are edge filters," Vis. Res., vol. 37, pp. 3327-3338, 1997.
37. T. Lee, M. Lewicki, and T. Sejnowski, "ICA mixture models for unsupervised classification of nongaussian classes and automatic context switching in blind separation," Pattern Anal. Mach. Intell., vol. 22, no. 10, Oct. 2000.
38. M. S. Bartlett, H. M. Lades, and T. J. Sejnowski, "Independent component representations for face recognition," in Proc. SPIE Conf. Human Vision and Electronic Imaging III, vol. 3299, 1998, pp. 528-539.
39. B. Moghaddam, "Principal manifolds and Bayesian subspaces for visual recognition," in Proc. Int. Conf. Computer Vision, Sep. 1999, citeseer.nj.nec.com/moghaddam99principal.html, pp. 1131-1136.
40. C. Liu and H. Wechsler, "Comparative assessment of independent component analysis (ICA) for face recognition," presented at the 2nd Int. Conf. Audio- and Video-based Biometric Person Authentication, Washington, DC, Mar. 1999.
41. R. Manduchi and J. Portilla, "Independent component analysis of textures," presented at the IEEE Int. Conf. Computer Vision, Corfu, Greece, 1999.
42. J. M. M. S. Bartlett and T. Sejnowski, "Face recognition by independent component analysis," IEEE Trans. Neural Netw., vol. 13, no. 5, pp. 1450-1464, Oct. 2002.
43. A. Hyvärinen and E. Oja, "Independent component analysis: Algorithms and applications," Neural Netw., vol. 13, no. 4, pp. 411-430, 2000.
44. D.-T Pham, P. Garrat, and C. Jutten, "Separation of a mixture of independent sources through a maximum likelihood approach," in Proc. EUSIPCO, 1992, pp. 771-774.
45. J.-F. Cardoso, "Blind signal separation: Statistical principles," Proc. IEEE, vol. 90, no. 10, pp. 2009-2025, Oct. 1998.
46. A. Hyvärinen and P. Hoyer, "Emergence of phase and shift invariant features by decomposition of natural images into independent feature subspaces," Neural Comput., vol. 12, no. 7, pp. 1705-1720, 2000.
47. T. Kohonen, "Emergence of invariant-feature detectors in the adaptive-subspace self-organizing maps," Biol. Cybern., vol. 75, pp. 281-291, 1996.
48. T. Kohonen, Self-Organizing Maps, 2nd ed, ser. Information Sciences. Heidelberg, Germany: Springer, 1997.
49. J.-F. Cardoso, "Multidimensional independent component anlysis," presented at the Int. Conf. Acoustic, Speech and Signal Processing, Seattle, WA, 1998.
50. A. P. Pentland, B. Moghaddam, and T. Starner, "View-based and modular eigenspaces for face recognition," in Proc. IEEE Computer Society Conf. Computer Vision and Pattern Recognition, 1994, pp. 84-91.
51. R. Fergus, P. Perona, and A. Zisserman, "Object class recognition by unsupervised scale-invariant learning," in Proc. IEEE Conf. Computer Vision and Pattern Recognition, Madison, WI, Jun. 2003.