JFET_V2_N3_RP5 G. Wiselin Jiji Dr. L. Ganesan Journal on Future Engineering and Technology 2230 – 7184 2 3 57 62 Gabor filter, classification, segmentation, SOMS, K-means Texture is an important spatial feature, useful for identifying objects or regions of interest in an image. Classification and Segmentation of textures in tissues is very difficult due to high variability of the data within and between images. In this paper, a visualization-based approach for training a texture classifier is presented. Powerful Gabor filter is used to extract texture feature and a self-organizing map (SOM) and K-Means are employed for visual training, segmentation and classification, providing very promising results in the classification and segmentation of tissues. From the results, it is evident that the incorporation of colour information enhanced the colour texture Classification and Segmentation and the developed frameworks are effective. February - April 2007 Copyright © 2007 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=822