Analysis and Synthesis of Textures With Pairwise Signal Interactions

The methods for the extraction of the main texture properties and for the subsequent texture synthesis are proposed based on the formal definitions of the essential statistical properties and the notion of texture in terms of pairwise and singleton signal interactions. The iterative synthesis procedure is a successive approximation in the space of the selected statistical properties towards the point corresponding to the reference texture properties. As a tool for the image sequence generation the stochastic relaxation mechanism is used. The image is assumed to be a state from the family of random fields. The proof of the convergence of the controlled stochastic generating procedure is included. Index Terms -texture, successive approximation, stochastic relaxation, random field

[1]  N. Metropolis,et al.  Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[2]  D. Brook.  On the distinction between the conditional probability and the joint probability approaches in the specification of nearest-neighbour systems , 1964 .

[3]  I. Z. Fisher,et al.  Statistical theory of liquids , 1964 .

[4]  P. L. Dobruschin.  The Description of a Random Field by Means of Conditional Probabilities and Conditions of Its Regularity , 1968 .

[5]  R. A. Silverman,et al.  Introductory Real Analysis , 1972 .

[6]  F. Spitzer.  Markov Random Fields and Gibbs Ensembles , 1971 .

[7]  J. Besag.  Nearest‐Neighbour Systems and the Auto‐Logistic Model for Binary Data , 1972 .

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

[9]  M. Hassner,et al.  The use of Markov Random Fields as models of texture , 1980 .

[10]  Anil K. Jain,et al.  Markov Random Field Texture Models , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[12]  Scott Kirkpatrick,et al.  Optimization by simulated annealing: Quantitative studies , 1984 .

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

[14]  E. Bonomi,et al.  The N-City Travelling Salesman Problem: Statistical Mechanics and the Metropolis Algorithm , 1984 .

[15]  Robert H. Swendsen,et al.  Statistical mechanics and disordered systems , 1985, CACM.

[16]  B. Gidas.  Nonstationary Markov chains and convergence of the annealing algorithm , 1985 .

[17]  Paolo Carnevali,et al.  Image Processing by Simulated Annealing , 1985, IBM J. Res. Dev..

[18]  Andrew Blake,et al.  Comparison of the Efficiency of Deterministic and Stochastic Algorithms for Visual Reconstruction , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Basilis Gidas,et al.  A Renormalization Group Approach to Image Processing Problems , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Nico Karssemeijer,et al.  A relaxation method for image segmentation using a spatially dependent stochastic model , 1990, Pattern Recognit. Lett..

[21]  Georgy L. Gimel'farb,et al.  Probabilistic models of digital region maps based on Markov random fields with short- and long-range interaction , 1993, Pattern Recognit. Lett..

[22]  Georgy L. Gimel'farb,et al.  Markov Random Fields with Short- and Long-Range Interaction for Modelling Gray-Scale Textured Images , 1993, CAIP.

[23]  Alexey Zalesny,et al.  Homogeneity & texture. General approach , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[24]  Roland Wilson,et al.  A two-component model of texture for analysis and synthesis , 1998, IEEE Trans. Image Process..