This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
The Quotient Image: Class-Based Re-Rendering and Recognition with Varying Illuminations
February 2001 (vol. 23 no. 2)
pp. 129-139

Abstract—The paper addresses the problem of “class-based” image-based recognition and rendering with varying illumination. The rendering problem is defined as follows: Given a single input image of an object and a sample of images with varying illumination conditions of other objects of the same general class, re-render the input image to simulate new illumination conditions. The class-based recognition problem is similarly defined: Given a single image of an object in a database of images of other objects, some of them are multiply sampled under varying illumination, identify (match) any novel image of that object under varying illumination with the single image of that object in the database. We focus on Lambertian surface classes and, in particular, the class of human faces. The key result in our approach is based on a definition of an illumination invariant signature image which enables an analytic generation of the image space with varying illumination. We show that a small database of objects—in our experiments as few as two objects—is sufficient for generating the image space with varying illumination of any new object of the class from a single input image of that object. In many cases, the recognition results outperform by far conventional methods and the re-rendering is of remarkable quality considering the size of the database of example images and the mild preprocess required for making the algorithm work.

[1] Y. Adini, Y. Moses, and S. Ullman, “Face Recognition: The Problem of Compensating for Changes in Illumination Direction,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 721-732, July 1997.
[2] J.J. Atick, P.A. Griffin, and N.A. Redlich, “Statistical Approach to Shape-from-Shading: Deriving 3D Face Surfaces from Single 2D Images,” Neural Computation, 1997.
[3] R. Basri, “Recognition by Prototypes,” Int'l J. Computer Vision, vol. 19, no. 2, pp. 147-168, 1996.
[4] P.N. Belhumeur, J.P. Hespanha, and D.J. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,” Proc. European Conf. Computer Vision, 1996.
[5] D. Beymer and T. Poggio, “Image Representations for Visual Learning,” Science, vol. 272, pp. 1905-1909, 1995.
[6] S. Edelman, “Class Similarity and Viewpoint Invariance in the Recognition of 3D Objects,” Biological Cybernetics, vol. 72, pp. 207-220, 1995.
[7] W.T. Freeman and J.B. Tenenbaum, “Learning Bilinear Models for Two-Factor Problems in Vision,” Proc. Computer Visualization and Pattern Recognition '97, June 1997.
[8] A. Georghiades, D. Kriegman, and P. Belhumeur, “Illumination Cones for Recognition under Variable Lighting: Faces,” Proc. Computer Vision and Pattern Recognition Conf., pp. 52-59, 1998.
[9] P. Hallinan, "A Low-Dimensional Representation of Human Faces for Arbitrary Lighting Conditions," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 1994, pp. 995-999.
[10] Y. Leedan and P. Meer, “Estimation with Bilinear Constraints in Computer Vision,” Proc. Sixth Int'l Conf. Computer Vision, pp. 733-738, Jan. 1998.
[11] M. Turk and A. Pentland, “Eigen Faces for Recognition,” J. Cognitive Neuroscience, vol. 3, no. 1, 1991.
[12] J. Nimeroff, E. Simoncelli, and J. Dorsey, “Efficient Re-rendering of Naturally Illuminated Environments,” Proc. Fifth Ann. Eurographics Symp. Rendering, June 1994.
[13] T. Poggio and T. Vetter, “Recognition and Structure from One 2D Model View: Observations on Prototypes, Object Classes and Symmetries,” Artificial Intelligence Memo 1347/CBIP Paper 69, Mass. Inst. of Tech nology, Feb. 1992.
[14] T. Riklin-Raviv, “The Quotient Image: Class-Based Re-rendering and Recognition with Varying Illuminations,” master's thesis, School of Computer Science and Eng., 2000.
[15] D.A. Rowland and D.I. Perrett, "Manipulating Facial Appearance through Shape and Color," IEEE Computer Graphics and Applications, vol. 15, no. 5, Sept. 1995, pp. 70-76.
[16] E. Sali and S. Ullman, “Recognizing Novel 3D Objects under New Illumination and Viewing Position Using a Small Number of Examples,” Proc. Int'l Conf. Computer Vision, pp. 153-161, 1998.
[17] C. Schoeneman, J. Dorsey, B. Smits, J. Arvo, and D. Greenburg, “Painting with Light,” Proc. ACM SIGGRAPH’93, pp. 143-146, 1993.
[18] A. Shashua, “Illumination and View Position in 3D Visual Recognition,” Advances in Neural Information Processing Systems 4, S. J. Hanson, J.E. Moody, and R.P. Lippmann, eds., pp. 404-411, San Mateo, Calif.: Morgan Kaufmann, 1992.
[19] A. Shashua, “On Photometric Issues in 3D Visual Recognition from a Single 2D Image,” Int'l J. Computer Vision, vol. 21, nos. 1-2, pp. 99-122, Jan. 1997.
[20] L. Sirovich and M. Kirby, “Low Dimensional Procedure for the Characterization of Human Faces,” J. Optical Soc. Am., vol. 4, no. 3, pp. 519-524, 1987.
[21] HSV is later institutionalized in the PostScript language—renamed HSB (B for brightness)—at the company Adobe Systems by its founder, John Warnock, another graduate of PARC (and the University of Utah before that); and see A.R. Smith, "Color Gamut Transform Pairs,"Computer Graphics, vol. 12, no. 3, Aug. 1978, pp. 12-19 (Siggraph 78 Conf. Proc.); reprinted inTutorial: Computer Graphics, second edition, J.C. Beatty and K.S. Booth, eds., IEEE Computer Soc. Press, Los Alamitos, Calif., 1982, pp. 376-383. Discusses the HSV algorithm.
[22] A. Stoschek, “Image-Based Re-rendering of Faces for Continuous Pose and Illumination Directions,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 582-587, June 2000.
[23] V.N. Vapnik, Statistical Learning Theory, John Wiley&Sons, 1998.
[24] T. Vetter and V. Blanz, “Estimating Coloured 3D Face Models from Single Images: An Example-Based Approach,” Proc. European Conf. Computer Vision, pp. 499-513, 1998.
[25] T. Vetter, M.J. Jones, and T. Poggio, “A Bootstrapping Algorithm for Learning Linear Models of Object Classes,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 40-46, 1997.
[26] T. Vetter and T. Poggio, “Image Synthesis from a Single Example View,” Proc. European Conf. Computer Vision, 1996.
[27] T. Vetter and T. Poggio, "Linear Object Classes and Image Synthesis from Single Example Image," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 733-741, July 1997.

Index Terms:
Visual recognition, image-based rendering, photometric alignment.
Citation:
Amnon Shashua, Tammy Riklin-Raviv, "The Quotient Image: Class-Based Re-Rendering and Recognition with Varying Illuminations," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 2, pp. 129-139, Feb. 2001, doi:10.1109/34.908964
Usage of this product signifies your acceptance of the Terms of Use.