The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.07 - July (2012 vol.34)
pp: 1437-1444
Qi Zhao , National University of Singapore, Singapore
Ping Tan , National University of Singapore, Singapore
Qiang Dai , Jilin University, Jilin
Li Shen , Institute for Infocomm Research, Singapore
Enhua Wu , Chinese Academy of Sciences, Beijing
Stephen Lin , Microsoft Research Asia, Beijing
ABSTRACT
We propose a method for intrinsic image decomposition based on retinex theory and texture analysis. While most previous methods approach this problem by analyzing local gradient properties, our technique additionally identifies distant pixels with the same reflectance through texture analysis, and uses these nonlocal reflectance constraints to significantly reduce ambiguity in decomposition. We formulate the decomposition problem as the minimization of a quadratic function which incorporates both the retinex constraint and our nonlocal texture constraint. This optimization can be solved in closed form with the standard conjugate gradient algorithm. Extensive experimentation with comparisons to previous techniques validate our method in terms of both decomposition accuracy and runtime efficiency.
INDEX TERMS
Intrinsic images, retinex, nonlocal constraint, texture.
CITATION
Qi Zhao, Ping Tan, Qiang Dai, Li Shen, Enhua Wu, Stephen Lin, "A Closed-Form Solution to Retinex with Nonlocal Texture Constraints", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.34, no. 7, pp. 1437-1444, July 2012, doi:10.1109/TPAMI.2012.77
REFERENCES
[1] Y. Weiss, "Deriving Intrinsic Images from Image Sequences," Proc. IEEE Int'l Conf. Computer Vision, vol. 2, pp. 68-75, 2001.
[2] Y. Matsushita, K. Nishino, K. Ikeuchi, and M. Sakauchi, "Illumination Normalization with Time-Dependent Intrinsic Images for Video Surveillance," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 1, pp. 3-10, 2003.
[3] Y. Matsushita, S. Lin, S.B. Kang, and H.-Y. Shum, "Estimating Intrinsic Images from Image Sequences with Biased Illumination," Proc. European Conf. Computer Vision, vol. 2, pp. 274-286, 2004.
[4] A. Agrawal, R. Raskar, and R. Chellappa, "Edge Suppression by Gradient Field Transformation Using Cross-Projection Tensors," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 2301-2308, 2006.
[5] E. Land and J. McCann, "Lightness and Retinex Theory," J. Optical Soc. of Am. A, vol. 3, pp. 1684-1692, 1971.
[6] B.V. Funt, M.S. Drew, and M. Brockington, "Recovering Shading from Color Images," Proc. European Conf. Computer Vision, pp. 124-132, 1992.
[7] R. Kimmel, M. Elad, D. Shaked, R. Keshet, and I. Sobel, "A Variational Framework for Retinex," Int'l J. Computer Vision, vol. 52, pp. 7-23, 2003.
[8] P. Sinha and E. Adelson, "Recovering Reflectance and Illumination in a World of Painted Polyhedra," Proc. IEEE Int'l Conf. Computer Vision, pp. 156-163, 1993.
[9] M. Bell and W.T. Freeman, "Learning Local Evidence for Shading and Reflectance," Proc. IEEE Int'l Conf. Computer Vision, vol. 1, pp. 670-677, 2001.
[10] M.F. Tappen, W.T. Freeman, and E.H. Adelson, "Recovering Intrinsic Images from a Single Image," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 9, pp. 1459-1472, Sept. 2005.
[11] M.F. Tappen, W.T. Freeman, and E.H. Adelson, "Estimating Intrinsic Component Images Using Non-Linear Regression," Proc. IEEE CS Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 1992-1999, 2006.
[12] W. Freeman, E. Pasztor, and O. Carmichael, "Learning Low-Level Vision," Int'l J. Computer Vision, vol. 40, pp. 24-57, 2000.
[13] T. Leung and J. Malik, "Representing and Recognizing the Visual Appearance of Materials Using Three-Dimensional Textons," Int'l J. Computer Vision, vol. 43, pp. 29-44, 2001.
[14] L. Shen, P. Tan, and S. Lin, "Intrinsic Image Decomposition with Non-Local Texture Cues," Proc. IEEE Conf. Computer Vision and Pattern Recognition, 2008.
[15] A. Bousseau, S. Paris, and F. Durand, "User-Assisted Intrinsic Images," ACM Trans. Graphics, vol. 28, no. 5,article 30, 2009.
[16] X. Jiang, A.J. Schofield1, and J.L. Wyatt, "Correlation-Based Intrinsic Image Extraction from a Single Image," Proc. European Conf. Computer Vision, 2010.
[17] J. Malik and P. Perona, "Preattentive Texture Discrimination with Early Vision Mechanisms," J. Optical Soc. of Am. A, vol. 7, pp. 923-932, 1990.
[18] S. Zhu, Y. Wu, and D. Mumford, "Filters, Random Fields and Maximum Entropy (Frame): Towards a Unified Theory for Texture Modeling," Int'l J. Computer Vision, vol. 27, pp. 107-126, 1998.
[19] A.A. Efros and T.K. Leung, "Texture Synthesis by Non-Parametric Sampling," Proc. IEEE Int'l Conf. Computer Vision, vol. 2, pp. 1033-1038, 1999.
[20] G.D. Finlayson, M.S. Drew, and C. Lu, "Entropy Minimization for Shadow Removal," Int'l J. Computer Vision, vol. 85, pp. 35-57, Oct. 2009.
[21] E. Parzen, "On Estimation of a Probability Density Function and Mode," The Annals of Math. Statistics, vol. 33, pp. 1065-1076, 1962.
[22] R. Grosse, M.K. Johnson, E.H. Adelson, and W.T. Freeman, "Ground Truth Dataset and Baseline Evaluations for Intrinsic Image Algorithms," Proc. IEEE Int'l Conf. Computer Vision, 2009.
558 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool