[1] H. Farid,H. Edward. Separating reflections from images using independent components analysis[J]. J. Opt. Soc. Am. A,1999,16(9):2136-2145

[2] Jian Ji,Zheng Tian. Blind noisy image separation based on a new robust independent component analysis network[J]. Chin. Opt. Lett.,2006,4(10):573-575

[3] Zhao Lin,Jin Weiqi,Chen Yinan et al.. Blind restoration for defocus blurred image based on autocorrelation of derivative image[J]. Acta Optica Sinica,2008,28(9):1703-1709

[4] P. Comon. Independent component analysis,a new concept[J]. Signal Process.,1994,36(1):287-314

[5] R. Szeliksi,S. Avidan,P. Anandan. Layer extraction from multiple images containing reflections and transparency[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2000. 246-253

[6] A. Levin,Y. Weiss. User assisted separation of reflections from a single image using a sparsity prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(9):1647-1654

[7] M. Yamazaki,Chen Yenwei,Xu Gang. Separation of reflection components by kernel independent component analysis[J]. Int. J. Comput. Sci. Network Security,2006,6(6):7-12

[8] F. Bach,M. I. Jordan. Kernel independent component analysis[J]. J. Machine Learning Res.,2002,3(7):1-48

[9] H. Shen,S. Jegelka,A. Gretton. Fast Kernel ICA using an Approximate Newton Method[C]. Proc. of the 11th International Conference on Artificial Intelligence and Statistics,San Juan,2007. 476-483

[10] H. Shen,S. Jegelka,A. Gretton. Fast kernel-based independent component analysis[J]. IEEE Tran. Signal Process.,2009,57(9):202-857

[11] Wu Yubin,Cao Danhua. Testing of nonuniformity of charge coupled image devices[J]. J. Huazhong University of Sci. Technol.,1998,26(8):58-60

[12] A. Gretton,O. Bousquet,A. J. Smola et al.. Measuring statistical dependence with Hilbert-Schmidt norms[C]. the 16th International Conference on Algorithmic Learning Theory,Singapore,2005,3734:63-78

[13] K. Hüper,J. Trumpf. Newton-like methods for numerical optimisation on manifolds[C]. Thirty-eighth Asilomar Conference on Signals,Systems and Computers,Pacific Grove,2004,1:136 -139

[14] S. Fine,K. Scheinberg. Efficient SVM training using low-rank kernel representations[J]. J. Machine Learning Res.,2001,2(22):243 -264