MetaCartSign in to MyCiteSeer

Include Citations | Advanced Search | Help

Include Citations | Advanced Search | Help

  the form UbI; L,

Download:
Download as a PDF
by Song Chun Zhu, David Mumford, Sg Afee
http://www.stat.ucla.edu/~sczhu/papers/Generic_prior.pdf
Add To MetaCart

Abstract:

Abstract—This article addresses two important themes in early visual computation: First, it presents a novel theory for learning the universal statistics of natural images—a prior model for typical cluttered scenes of the world—from a set of natural images, and, second, it proposes a general framework of designing reaction-diffusion equations for image processing. We start by studying the statistics of natural images including the scale invariant properties, then generic prior models were learned to duplicate the observed statistics, based on the minimax entropy theory studied in two previous papers. The resulting Gibbs distributions have potentials of

Citations

2322 Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images – Geman, Geman - 1984
658 Scale-space and edge detection using anisotropic diffusion – Perona, Malik - 1990
546 A maximum entropy approach to natural language processing – Berger, Pietra, et al. - 1996
536 Visual Reconstruction – Blake, Zisserman - 1987
439 Theory of communication – Gabor - 1946
433 Optimal approximations by piecewise smooth functions and associated variational problems – Mumford, Shah - 1989
425 Solution of Ill-posed Problems – Tikhonov, Arsenin - 1977
358 Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters – Daugman - 1985
357 Region Competition: Unifying Snakes, Region Growing, and Bayes/MDL for Multiband Image Segmentation – Zhu, Yuille - 1996
348 Relations between the statistics of natural images and the response properties of cortical cells – Field - 1987
209 Robust Regression Methods for Computer Vision – Meer, Mintz, et al. - 1991
159 Generating textures on arbitrary surfaces using reactiondiffusion – Turk - 1991
146 Image analysis, random fields, and dynamic Monte Carlo methods : a mathematical introduction. Berlin – Winkler - 1995
140 Robust anisotropic diffusion – Black, Sapiro, et al. - 1998
134 Minimax entropy principle and its application to texture modeling – Zhu, Wu, et al. - 1997
130 On the unification of line processes, outlier rejection, and robust statistics with applications in early vision – Black, Rangarajan - 1996
96 Reaction-diffusion textures – Kass - 1991
72 A common framework for image segmentation – Geiger, Yuille - 1991
58 Nonlinear image filtering with edge and corner enhancement – Nitzberg, Shiota - 1992
56 Multilevel computational processes for visual surface reconstruction – Terzopoulos - 1983
50 A renormalization group approach to image processing problems – Gidas - 1989
48 A Theory of Networks for Approximation and – Poggio, Girosi - 1989
33 Diffusions for global optimization – Geman, Hwang - 1986
29 Parallel and deterministic algorithms for mrfs: surface reconstruction – Geiger, Girosi - 1991
29 A model for the formation of ocular dominance stripes – Swindale - 1980
23 Statistics of Natural images: Scaling in the – Ruderman, Bialek - 1994
15 Learning Generic Prior Models for Visual Computation – Zhu, Mumford - 1997
9 M-lattice: from morphogenesis to image processing – Sherstinsky, Picard - 1996
8 The Theory and Applications of Reaction-Diffusion Equations – Grindrod - 1996
8 Probabilistic Solution of Ill-Posed Problems in – Marroquin, Mitter, et al. - 1987
8 The chemical basis of morphogenesis,” Philosophical – Turing - 1952
5 A pre-pattern formation mechanism for mammalian coat markings – Murray - 1981
5 A general framework for geometry-driven evolution equations – Niessen - 1997
4 Constrained restoration and the recover of discontinuities – Geman, Reynoids - 1992
3 Efficiency of Model Human Image – Watson - 1987
1 On Sampling Methods and Annealing Algorithms,” Markov Random Fields—Theory and Applications – Gelfand, Mitter - 1993
1 Deformations I: The Components of Two-Dimensional Shape and – Kimia, Tannebaum, et al. - 1997
1 The Renormalization Group: Critical Phenomena and the Knodo Problem – Wilson - 1975
1 Random Fields, and Minimax Entropy (FRAME): Towards a Unified Theory for Texture Modeling – Zhu, Wu, et al. - 1996