nips nips2003 nips2003-88 nips2003-88-reference knowledge-graph by maker-knowledge-mining

88 nips-2003-Image Reconstruction by Linear Programming


Source: pdf

Author: Koji Tsuda, Gunnar Rätsch

Abstract: A common way of image denoising is to project a noisy image to the subspace of admissible images made for instance by PCA. However, a major drawback of this method is that all pixels are updated by the projection, even when only a few pixels are corrupted by noise or occlusion. We propose a new method to identify the noisy pixels by 1 -norm penalization and update the identified pixels only. The identification and updating of noisy pixels are formulated as one linear program which can be solved efficiently. Especially, one can apply the ν-trick to directly specify the fraction of pixels to be reconstructed. Moreover, we extend the linear program to be able to exploit prior knowledge that occlusions often appear in contiguous blocks (e.g. sunglasses on faces). The basic idea is to penalize boundary points and interior points of the occluded area differently. We are able to show the ν-property also for this extended LP leading a method which is easy to use. Experimental results impressively demonstrate the power of our approach.


reference text

[1] A. Ben Hamza and H. Krim. Image denoising: A nonlinear robust statistical approach. IEEE Trans. Signal Processing, 49(12):3045–3054, 2001.

[2] M.J. Black and A. Rangarajan. On the unification of line processes, outlier rejection, and robust statistics with applications in early vision. International Journal of Computer Vision, 25(19):57–92, 1996.

[3] V. Blanz and T. Vetter. A morphable model for the synthesis of 3D faces. In SIGGRAPH’99 Conference Proceedings, pages 187–194, 1999.

[4] A.B.A. Graf and F.A. Wichmann. Gender classification of human faces. In H.H. B¨ lthoff, S.-W. Lee, T.A. Poggio, and C. Wallraven, editors, Biologically Motivated u Computer Vision 2002, LNCS 2525, pages 491–501, 2002.

[5] O.L. Mangasarian. Machine learning via polyhedral concave minimization. Technical Report 95-20, Computer Sciences Department, University of Wisconsin, 1995.

[6] S. Mika, B. Sch¨ lkopf, A.J. Smola, K.-R. M¨ ller, M. Scholz, and G. R¨ tsch. Kernel o u a PCA and de–noising in feature spaces. In M.S. Kearns, S.A. Solla, and D.A. Cohn, editors, Advances in Neural Information Processing Systems, volume 11, pages 536– 542. MIT Press, 1999.

[7] G. R¨ tsch, B. Sch¨ lkopf, A.J. Smola, S. Mika, T. Onoda, and K.-R. M¨ ller. Robust a o u ensemble learning. In A.J. Smola, P.L. Bartlett, B. Sch¨ lkopf, and D. Schuurmans, o editors, Advances in Large Margin Classifiers, pages 207–219. MIT Press, Cambridge, MA, 2000.

[8] B. Sch¨ lkopf, A. Smola, R.C. Williamson, and P.L. Bartlett. New support vector alo gorithms. Neural Computation, 12:1207 – 1245, 2000. also NeuroCOLT Technical Report NC-TR-1998-031.

[9] T. Takahashi and T. Kurita. Robust de-noising by kernel PCA. In J.R. Dorronsoro, editor, Artificial Neural Networks – ICANN 2002, LNCS 2415, pages 727–732. Springer Verlag, 2002.