Stochastic and deterministic networks for texture segmentation

Several texture segmentation algorithms based on deterministic and stochastic relaxation principles, and their implementation on parallel networks, are described. The segmentation process is posed as an optimization problem and two different optimality criteria are considered. The first criterion involves maximizing the posterior distribution of the intensity field given the label field (maximum a posteriori estimate). The posterior distribution of the texture labels is derived by modeling the textures as Gauss Markov random fields (GMRFs) and characterizing the distribution of different texture labels by a discrete multilevel Markov model. A stochastic learning algorithm is proposed. This iterated hill-climbing algorithm combines fast convergence of deterministic relaxation with the sustained exploration of the stochastic algorithms, but is guaranteed to find only a local minimum. The second optimality criterion requires minimizing the expected percentage of misclassification per pixel by maximizing the posterior marginal distribution, and the maximum posterior marginal algorithm is used to obtain the corresponding solution. All these methods implemented on parallel networks can be easily extended for hierarchical segmentation; results of the various schemes in classifying some real textured images are presented. >

[1]  José L. Marroquín,et al.  Probabilistic solution of inverse problems , 1985 .

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

[3]  Haluk Derin,et al.  Modeling and Segmentation of Noisy and Textured Images Using Gibbs Random Fields , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Kumpati S. Narendra,et al.  Learning Automata - A Survey , 1974, IEEE Trans. Syst. Man Cybern..

[5]  R. Chellappa.  Two-Dimensional Discrete Gaussian Markov Random Field Models for Image Processing , 1989 .

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

[7]  Rama Chellappa,et al.  Classification of textures using Gaussian Markov random fields , 1985, IEEE Trans. Acoust. Speech Signal Process..

[8]  Tomaso Poggio,et al.  Computational vision and regularization theory , 1985, Nature.

[9]  Richard Wheeler,et al.  Decentralized learning in finite Markov chains , 1985, 1985 24th IEEE Conference on Decision and Control.

[10]  J. Besag.  On the Statistical Analysis of Dirty Pictures , 1986 .

[11]  David B. Cooper,et al.  Simple Parallel Hierarchical and Relaxation Algorithms for Segmenting Noncausal Markovian Random Fields , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  T. Poggio,et al.  A parallel algorithm for real-time computation of optical flow , 1989, Nature.

[13]  Rama Chellappa,et al.  Stereo matching using a neural network , 1988, ICASSP-88., International Conference on Acoustics, Speech, and Signal Processing.

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

[15]  B. K. Jenkins,et al.  Image restoration using a neural network , 1988, IEEE Trans. Acoust. Speech Signal Process..

[16]  Mandayam A. L. Thathachar,et al.  Relaxation Labeling with Learning Automata , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Jin Luo,et al.  Computing Motion Using Resistive Networks , 1988, Photonics West - Lasers and Applications in Science and Engineering.

[18]  Y. T. Zhou,et al.  Computation of optical flow using a neural network , 1988, IEEE 1988 International Conference on Neural Networks.