Surface Dependent Representations for Illumination Insensitive Image Comparison
January 2007 (vol. 29 no. 1)
pp. 98-111
DOI Bookmark:
http://doi.ieeecomputersociety.org/10.1109/TPAMI.2007.19
We consider the problem of matching images to tell whether they come from the same scene viewed under different lighting conditions. We show that the surface characteristics determine the type of image comparison method that should be used. Previous work has shown the effectiveness of comparing the image gradient direction for surfaces with material properties that change rapidly in one direction. We show analytically that two other widely used methods, normalized correlation of small windows and comparison of multiscale oriented filters, essentially compute the same thing. Then, we show that for surfaces whose properties change more slowly, comparison of the output of whitening filters is most effective. This suggests that a combination of these strategies should be employed to compare general objects. We discuss indications that Gabor jets use such a mixed strategy effectively, and we propose a new mixed strategy. We validate our results on synthetic and real images.
[1] R.J. Adler, The Geometry of Random Fields. John Wiley and Sons, 1981.[2] R. Basri and D. Jacobs, “Lambertian Reflectance and Linear Subspaces,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 2, pp. 218-233, Feb. 2003.[3] M. Bichsel, “Strategies of Robust Object Recognition for the Automatic Identification of Human Faces,” PhD thesis, no. 9467, ETH Zurich, 1991.[4] R. Brunelli, “Estimation of Pose and Illuminant Direction for Face Processing,” MIT AI Memo 1499, 1994.[5] C. Bregler and J. Malik, “Learning Appearance Based Models: Mixtures of Second Moment Experts,” Advances in Neural Information Precessing Systems 9, pp. 845-851, 1997.[6] T. Brunelli and T. Poggio, “Face Recognition: Features versus Templates,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 10, pp. 1042-1062, Oct. 1993.[7] H. Chen, P. Belhumeur, and D. Jacobs, “In Search of Illumination Invariants,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. I, pp. 254-261, 2000.[8] T. Cootes and C. Taylor, “On Representing Edge Structure for Model Matching,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. I, pp. 1114-1119, 2001.[9] R.O. Duda and P.E. Hart, and D.G. Stork, Pattern Classification. Wiley, 2001.[10] P. Felzenszwalb and D. Huttenlocher, “Pictorial Structures for Object Recognition,” to appear.[11] A. Fitch, A. Kadyrov, W. Christmas, and J. Kittler, “Orientation Correlation,” Proc. British Machine Vision Conf., vol. 1, pp. 133-142, 2002.[12] W. Freeman, D. Anderson, P. Beardsley, C. Dodge, M. Roth, C. Weissman, W. Yerazunis, H. Kage, K. Kyuma, Y. Miyake, and K. Tanaka, “Computer Vision for Interactive Computer Graphics,” IEEE Computer Graphics and Applications, vol. 18, no. 3, May/June 1998.[13] D. Forsyth and J. Ponce, Computer Vision: A Modern Approach. Prentice-Hall, 2003.[14] D. Gabor, “Theory of Communication,” J. IEEE, vol. 93, pp. 429-457, 1946.[15] T. Gevers and A.W.M. Smeulders, “Color Constant Ratio Gradients for Image Segmentation and Similarity of Textured Objects,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 18-25, 2001.[16] A.S. Georghiades, P.N. Belhumeur, and D.J. Kriegman, “From Few to Many: Generative Models for Recognition under Variable Pose and Illumination,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 6, pp. 643-660, June 2001.[17] R. Gonzalez and R. Woods, Digital Image Processing. Anderson-Wesley, 1992.[18] H. Greenspan, S. Belongie, R. Goodman, P. Perona, S. Rakshit, and C. Anderson, “Overcomplete Steerable Pyramid Filters and Rotation Invariance,” Proc. Conf. Computer Vision and Pattern Recognition, pp. 222-228, 1994.[19] R. Gross and V. Brajovic, “An Image Preprocessing Algorithm for Illumination Invariant Face Recognition,” Proc. Fourth Int'l Conf. Audio and Video-Based Biometric Person Authentication, pp. 10-18, 2003.[20] R.M. Haralick and L.G. Shapiro, Computer and Robot Vision. Addison-Wesley, 1992.[21] D. Hond and L. Spacek, “Distinctive Descriptions for Face Processing,” Proc. Eighth British Machine Vision Conf., vol. 1, pp.320-329, 1997.[22] B. Jähne, Digital Image Processing. Springer-Verlag, 1995.[23] A.K. Jain, Fundamentals of Digital Image Processing. Prentice Hall, 1989.[24] F. Jiao, S. Li, H. Shum, and D. Schuurmans, “Face Alignment Using Statistical Models and Wavelet Features,” Proc. Conf. Computer Vision and Pattern Recognition, 2003.[25] D. Keren, M. Osadchy, and C. Gotsman, “Antifaces: A Novel, Fast Method for Image Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 7, pp. 747-761, July 2001.[26] J. Kittler, Y. Li, and J. Matas, “On Matching Scores for LDA-Based Face Verification,” Proc. 11th British Machine Vision Conf., vol. 1, pp. 42-51, 2000.[27] J.J. Koenderink and S.C. Pont, “Irradiation Direction from Texture,” J. Optical Soc. of Am. A, vol. 20, no. 10, pp. 1875-1882, 2003.[28] J.J. Koenderink and A. van Doorn, “Representation of Local Geometry in the Visual System,” Biological Cybernetics, vol. 55, pp.367-375, 1987.[29] E. Land and J. McCann, “Lightness and Retinex Theory,” J. Optical Soc. of Am., vol. 61, no. 1, pp. 1-11, 1971.[30] M. Lades, J.C. Vortbrüggen, J. Buhmann, J. Lange, C. von der Malsburg, R.P. Würtz, and W. Konen, “Distortion Invariant Object Recognition in the Dynamic Link Architecture,” IEEE Trans. Computers, vol. 42, pp. 300-311, 1993.[31] S. Narasimhan, V. Ramesh, and S. Nayar, “A Class of Photometric Invariants: Separating Material from Shape and Illumination,” Proc. Int'l Conf. Computer Vision, pp. 1387-1394, 2003.[32] S.K. Nayar and R.M. Bolle, “Reflectance Based Object Recognition,” Int'l J. Computer Vision, vol. 17, no. 3, pp. 219-240, Mar. 1996.[33] M. Oren and S.K. Nayar, “A Theory of Specular Surface Geometry,” Int'l J. Computer Vision, vol. 24, no. 2, pp. 105-124, 1997.[34] M. Osadchy, M. Lindenbaum, and D. Jacobs, “Whitening for Photometric Comparison of Smooth Surfaces under Varying Illumination,” Proc. European Conf. Computer Vision, pp. 217-228, 2004.[35] M. Osadchy, D. Jacobs, and M. Lindenbaum, “On the Equivalence of Common Approaches to Lighting Insensitive Recognition,” Proc. IEEE Int'l Conf. Computer Vision, vol. 2, pp.1721-1726, 2005.[36] M. Osadchy, D. Jacobs, and R. Ravamoorthi, “Using Specularities for Recognition,” Proc. IEEE Int'l Conf. Computer Vision, vol. 2, pp.1512-1519, 2003.[37] A. Papoulis, Probability, Random Variables, and Stochastic Processes, third ed. McGraw Hill, 1991.[38] P.J. Phillips and Y. Vardi, “Efficient Illumination Normalization of Facial Images,” Pattern Recognition Letters, vol. 17, pp. 921-927, 1996.[39] W. Pratt, Digital Image Processing, first ed. Wiley, 1978.[40] R. Rao and D. Ballard, “An Active Vision Architecture Based on Iconic Representations,” Artificial Intelligence, pp. 461-505, 1995.[41] S. Ravela and C. Luo, “Appearance-Based Global Similarity Retrieval of Images,” Advances in Information Retrieval, 2000.[42] C. Schmid and R. Mohr, “Local Grayvalue Invariants for Image Retrieval,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 5, pp. 530-535, May 1997.[43] 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, 1997.[44] A. Shashua and T. Riklin-Raviv, “The Quotient Image: Class-Based Re-Rendering and Recognition with Varying Illuminations,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 23, no. 2, pp. 129-139, Feb. 2001.[45] D.A. Slater and G. Healey, “The Illumination-Invariant Recognition of 3D Objects Using Local Color Invariants,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 2, pp. 206-210, Feb. 1996.[46] E. Trucco and A. Verri, Introductory Techniques for 3-D Computer Vision. Prentice-Hall, 1998.[47] H.L. VanTrees, Detection, Estimation, and Modulation Theory, Part I, Wiley, 1965.[48] M. Varma and A. Zisserman, “Estimating Illumination Direction from Textured Images,” Proc. Conf. Computer Vision and Pattern Recognition, vol. I, pp. 179-186, 2004.[49] L. Wiskott, “Labeled Graphs and Dynamic Link Matching for Face Recognition and Scene Analysis,” PhD thesis, 1995.[50] L. Wiskott, J. Fellous, N. Kruger, and C. van der Malsburg, “Face Recognition by Elastic Graph Matching,” Intelligent Biometric Techniques in Fingerprint and Face Recognition, pp. 355-396, 1999.[51] L. Wolff and J. Fan, “Segmentation of Surface Curvature with a Photometric Invariant,” J. Optical Soc. of Am. A, vol. 11, no. 11, pp.3090-3100, 1994.
Index Terms:
Image comparison, Illumination, Gaussian random surface,Whitening.
Citation:
Margarita Osadchy, David W. Jacobs, Michael Lindenbaum, "Surface Dependent Representations for Illumination Insensitive Image Comparison," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 29, no. 1, pp. 98-111, Jan. 2007, doi:10.1109/TPAMI.2007.19
Usage of this product signifies your acceptance of the
Terms of Use.
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||