A Novel Fuzzy Rule Based Hybrid Technique for Image Segmentation

Abstract: Image segmentation is the process of partitioning a digital image into multiple segments to simplify its representation and converting it into something that is more meaningful and easier to analyze. Main goal of this paper is to segment a medical image using hybrid and fuzzy techniques to target the part that is to be diagnosed. It is difficult to analyze a medical image because of very similar grey levels or intensity values. Fuzzy is combined with hybrid segmentation technique to resolve ambiguities in the presence of insignificant data. The proposed algorithm uses different rules to resolve the regions which have similar edges. The results are evaluated on the basis of time, variation and accuracy of the segmented image. Efficiency achieved is satisfactory.

Keywords: Hybrid Segmentation, KFCM, FCM, Fuzzy Rule Based Segmentation.