Mean field annealing using compound Gauss-Markov random fields for edge detection and image estimation

The authors consider the problem of edge detection and image estimation in nonstationary images corrupted by additive Gaussian noise. The noise-free image is represented using the compound Gauss-Markov random field developed by F.C. Jeng and J.W. Woods (1990), and the problem of image estimation and edge detection is posed as a maximum a posteriori estimation problem. Since the a posteriori probability function is nonconvex, computationally intensive stochastic relaxation algorithms are normally required. A deterministic relaxation method based on mean field annealing with a compound Gauss-Markov random (CGMRF) field model is proposed. The authors present a set of iterative equations for the mean values of the intensity and both horizontal and vertical line processes with or without taking into account some interaction between them. The relationship between this technique and two other methods is considered. Edge detection and image estimation results on several noisy images are included.

[1]  Rama Chellappa,et al.  Pyramid implementation of optimal-step conjugate-search algorithms for some low-level vision problems , 1989, IEEE Trans. Syst. Man Cybern..

[2]  Federico Girosi,et al.  Parallel and deterministic algorithms from MRFs: surface reconstruction and integration , 1990, ECCV.

[3]  Wesley E. Snyder,et al.  Restoration of piecewise constant images by mean-field annealing , 1989 .

[4]  John W. Woods,et al.  Compound Gauss-Markov random fields for image estimation , 1991, IEEE Trans. Signal Process..

[5]  Tomaso Poggio,et al.  Probabilistic Solution of Ill-Posed Problems in Computational Vision , 1987 .

[6]  C. Campell,et al.  Statistical mechanics and neural networks , 1989 .

[7]  Wesley E. Snyder,et al.  Mean field annealing: a formalism for constructing GNC-like algorithms , 1992, IEEE Trans. Neural Networks.

[8]  J. Besag.  Spatial Interaction and the Statistical Analysis of Lattice Systems , 1974 .

[9]  John W. Woods,et al.  Simulated annealing in compound Gaussian random fields , 1990, IEEE Trans. Inf. Theory.

[10]  Nikitas J. Dimopoulos,et al.  PARALLEL ALGORITHMS FOR LOW-LEVEL VISION ON , 1994 .

[11]  Rama Chellappa,et al.  A model-based approach for estimation of two-dimensional maximum entropy power spectra , 1985, IEEE Trans. Inf. Theory.

[12]  Anand Rangarajan,et al.  Generalized graduated nonconvexity algorithm for maximum a posteriori image estimation , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[13]  John W. Woods,et al.  Two-dimensional discrete Markovian fields , 1972, IEEE Trans. Inf. Theory.

[14]  C Koch,et al.  Analog "neuronal" networks in early vision. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[15]  Andrew Blake,et al.  Visual Reconstruction , 1987, Deep Learning for EEG-Based Brain–Computer Interfaces.

[16]  Heinrich H. Bülthoff,et al.  Stereo Integration, Mean Field Theory and Psychophysics , 1990, ECCV.

[17]  J. Laurie Snell,et al.  Markov Random Fields and Their Applications , 1980 .

[18]  Josiane Zerubia,et al.  Mean field approximation using compound Gauss-Markov random field for edge detection and image restoration , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[19]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[21]  R. Chellappa,et al.  On two-dimensional Markov spectral estimation , 1983 .

[22]  John G. Harris,et al.  Generalized smoothing networks in early vision , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.