Model based region segmentation using cooccurrence matrices

A region segmentation algorithm is presented, using a model for joint probability density. Joint probability density can be defined as an N*N cooccurrence matrix in which each coordinate (i, j) gives the probability for the gray-level transition i, j between two neighbor pixels. The approach consists in modeling the energy distribution within a cooccurrence matrix of a region. Regions are assumed to be stationary. A region-growing scheme that proceeds in two steps is used. The first step consists of learning the parameters of the model. The second step is the segmentation process. Starting with a seed pixel, new pixels are incorporated in the region if their neighborhoods fit the model.<<ETX>>

[1]  Patrick C. Chen,et al.  Segmentation by texture using a co-occurrence matrix and a split-and-merge algorithm☆ , 1979 .

[2]  Erica M. Rounds,et al.  Segmentation Based On Second-Order Statistics , 1980, Optics & Photonics.

[3]  J. Boyce,et al.  Unification of image segmentation and edge detection , 1990 .

[4]  Mohan M. Trivedi,et al.  Object detection based on gray level cooccurrence , 1984, Comput. Vis. Graph. Image Process..

[5]  Calvin C. Gotlieb,et al.  Texture descriptors based on co-occurrence matrices , 1990, Comput. Vis. Graph. Image Process..

[6]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[7]  Chin-Tu Chen,et al.  Split-and-merge image segmentation based on localized feature analysis and statistical tests , 1991, CVGIP Graph. Model. Image Process..

[8]  Martin D. Levine,et al.  Low Level Image Segmentation: An Expert System , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  S. Pal,et al.  Segmentation based on measures of contrast, homogeneity, and region size , 1987, IEEE Transactions on Systems, Man, and Cybernetics.