Identification of Brain Tumor Using Texture Segmentation

Texture segmentation plays a vital role in many medical imaging applications. Texture segmentation is the process of partitioning an image into regions based on their texture. Here we present an unsupervised segmentation, which means that the algorithm does not require any knowledge of texture type present nor, the number of textures in the image to be segmented. The basic idea of the proposed method is to use the newly improved multi-resolution Gabor filter for feature extraction along with k-means clustering algorithm to group the related textures (segmenting the regions). This method is applied to segment a brain tumor images to identify the infected area.