Hybrid FCM with Watershed Algorithm for Image Segmentation
B. Sudhakar, A. Srinivasa Reddy · International Journal of Engineering Trends and Technology · 2014
Abstract – Image segmentation is rapidly applied in the field of image processing. In this paper a new method is suggested for implementing image segmentation. To overcome the problems of conventional threshold segmentation technique, an adaptive local threshold procedure is suggested. This method works well with images having non uniform intensity. The challenge of traditional Watershed Segmentation segmentation technique can be excluded by employing kernel based segmentation technique. Proposed fuzzy segmentation technique can be used for images having unequal dimension clusters. To overcome the noise sensitive of conventional Watershed Segmentation clustering algorithm, a novel extensive FCM SEGMENTATION algorithm for image segmentation is introduced in this paper. The method is developed by enhancing the objective component of the typical FCM SEGMENTATION algorithm with a cost term that considers the purpose of the neighbor pixels on the centre pixels. Research on the medical images show that proposed technique has significantly better clustering efficiency.