The segmentation of the image refers to extracting the needed region of interest from the image based on some specified methodologies. The segmentation methodologies are commonly based on thresholding (i.e.) the regions within the particular range or pixels that are having particular value. Edge detection, Contour extraction, Clustering are all segmentation methodologies. Edge detection identifies the edge points around the needed objects. Contour extraction refers to outlining the segmented portion from the image. Clustering refers to producing separate identifications (i.e.) color, contour differences for the regions in the image that are similar in intensity or similar in color. The images containing tumorous portions were collected. The obtained images were trained. The test image is preprocessed inorder to remove the noises from the image using median filter. Threshold is applied to the image and based on that the regions in the images are segmented. The region of interest (ROI) is selected from the threshold applied image. The ROI contains the tumorous and non tumorous portions. Corner points were detected from the image based on SIFT descriptors and the neighborhood regions around the each point extracted is taken. The features were extracted from the neighborhood regions and the values were saved as features. While training each neighborhood regions were labelled as tumor and normal region. Fuzzy rules were generated for the features obtained and based on the generated each neighborhood positions were identified as Tumor or Normal regions. The neighboring regions that are identified as tumors were whitened and the remaining portions were blackened so that the tumor portion is segmented separately. The performance of the process is measured by measuring the accuracy of the segmentation process.