iccv iccv2013 iccv2013-422 iccv2013-422-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Yuqian Zhang, Cun Mu, Han-Wen Kuo, John Wright
Abstract: Illumination variation remains a central challenge in object detection and recognition. Existing analyses of illumination variation typically pertain to convex, Lambertian objects, and guarantee quality of approximation in an average case sense. We show that it is possible to build models for the set of images across illumination variation with worstcase performance guarantees, for nonconvex Lambertian objects. Namely, a natural verification test based on the distance to the model guarantees to accept any image which can be sufficiently well-approximated by an image of the object under some admissible lighting condition, and guarantees to reject any image that does not have a sufficiently good approximation. These models are generated by sampling illumination directions with sufficient density, which follows from a new perturbation bound for directional illuminated images in the Lambertian model. As the number of such images required for guaranteed verification may be large, we introduce a new formulation for cone preserving dimensionality reduction, which leverages tools from sparse and low-rank decomposition to reduce the complexity, while controlling the approximation error with respect to the original model. 1
[1] R. Basri and D. Jacobs. Lambertian reflectance and linear subspaces. PAMI, 25:218–233, 2003. 1, 2, 6, 7
[2] P. Belhumeur and D. Kriegman. What is the set of images of
[3]
[4]
[5]
[6]
[7]
[8]
[9]
[10]
[11]
[12]
[13] an object under all possible illumination conditions? IJCV, 28:270–277, 1998. 1, 2, 3 E. Bronshteyn and D. Ivanov. The approximation of convex sets by polyhedra. Siberian Math. J., 1976. 6 E. Cand e`s, X. Li, Y. Ma, and J. Wright. Robust principal component analysis? JACM, 58(7), May 2011. 2, 6 V. Chandrasekaran, S. Sanghavi, P. Parillo, and A. Wilsky. Rank-sparsity incoherence for matrix decomposition. SIAM Journal on Optimization, 21(2):572–596, 2011. 2 T. Chen, W. Yin, X. S. Zhou, D. Domaniciu, , and T. Huang. Illumination normalization for face recognition and uneven background correction using total variation based image models. In CVPR, 2005. 1 T. F. Cootes, G. J. Edwards, and C. J. Taylor. Active appearance models. PAMI, 23:681–685, 2001 . 8 D. Frolova, D. Simakov, and R. Basri. Accuracy of spherical harmonic approximations for images of lambertian objects under far and near lighting. In ECCV, 2004. 1, 2 A. S. Georghiades, P. N. Belhumeur, and D. J. Kriegman. From few to many: Illumination cone models for face recognition under variable lighting and pose. PAMI, 23(6):643– 660, June 2001. 1, 7, 8 B. He and X. Yuan. On the o(1/n) convergence rate of the douglas-rachford alternating direction method. SIAM Journal on Numerical Analysis, 50(2):700–709, 2012. 6 B. K. Horn. Robot Vision. 1st edition, 1986. 5 K.-C. Lee, J. Ho, and D. J. Kriegman. Acquiring linear subspaces for face recognition under variable lighting. PAMI, 27(5):684–698, May 2005. 1 D. G. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 60(2):91–1 10, Nov. 2004. 1
[14] X. Mei, H. Ling, and D. Jacobs. Sparse representation of cast shadows via l1-regularized least squares. In ICCV, 2009. 1
[15] R. Ramamoorthi. Analytic pca construction for theoretical analysis of lighting variability in images of a lambertian object. PAMI, 24(10): 1322–1333, Oct. 2002. 1, 2
[16] R. Ramamoorthi, M. Koudelka, and P. Belhumeur. A fourier theory for cast shadows. PAMI, 27(2), 2005. 1
[17] A. Savran, B. Sankur, and M. Taha Bilge. Comparative evaluation of 3d vs. 2d modality for automatic detection of facial action units. Pattern Recognition, 45(2):767–782, 2012. 2
[18] A. Shashua and T. Riklin-Raviv. The quotient image: Classbased re-rendering and recognition with varying illuminations. PAMI, 23: 129–139, 2001. 1
[19] A. Wagner, J. Wright, A. Ganesh, Z. Zhou, H. Mobahi, and Y. Ma. Toward a practical face recognition system: Robust alignment and illumination by sparse representation. PAMI, 34(2):372–386, 2012. 1, 8
[20] Y. Wang, L. Zhang, Z. Liu, G. Hua, Z. Wen, Z. Zhang, and D. Samaras. Face relighting from a single image under arbitrary unknown lighting conditions. PAMI, 3 1(11), 2009. 1, 8
[21] J. Wright, A. Yang, A. Ganesh, S. Sastry, and Y. Ma. Robust face recognition via sparse representation. PAMI, 3 1(2), 2009. 1, 2, 6, 7
[22] L. Wu, A. Ganesh, B. Shi, Y. Matsushita, Y. Wang, and Y. Ma. Robust photometric stereo via low-rank matrix completion and recovery. In ACCV, 2010. 2, 6
[23] X. Zhang, M. Burger, X. Bresson, and S. Osher. Bregmanized nonlocal regularization for deconvolution and sparse reconstruction. SJIS, 3(3):253–276, 2010. 6 994444