Texture Image Segmentation Using Gabor Filter and Anisotropic Diffusion Filter

Abstract

Image segmentation is very important task in many image analysis or computer vision applications. In this paper a texture
image segmentation method using Gabor filter, anisotropic filter, and k-mean clustering algorithm was proposed. The Gabor filter was used as a multi-channels filter to analyze the texture in the image. The extraction and enhancement of the texture features obtained using anisotropic diffusion filter. Then the k-mean algorithm used to cluster pixels into number of clusters
representing the texture regions. The quality of segmentation using this method was evaluated using Ultimate Measurement
Accuracy (UMA) metric. The experiments show that the performance of this method is effective, accurate and gives better
results as compared with the Seo method from the view of quality of segmentation, the number of run times, the execution time and the capability of separating a large number of textures, and of segmented real images, random mosaics texture images, area of roofs and ground images, and to distinguish objects from background.