In this paper we describe a two-level system for the segmentation of texture images into regions of common textural properties. The first level is a purely numeric Texture Analyzer which uses texture energy measures to transform the image into feature measure planes. The second level is a Knowledge-Based Segmentor which applies heuristic rules, derived from knowledge of the image forming process, to arrive Qt a segmentation. We discuss two different control schemes that can be used to uide the segmentation process. These are based on paraflel region growing and iterative quadtree splitting respectively. An illustration of the performance of the system with both control schemes on a real test image is also presented.

M. Simaan

Papers

Knowledge-guided s egmentation of texture images