Enhanced Fuzzy-Based Models for ROI Extraction in Medical Images
Standard Fuzzy C-Means (FCM) clustering has been widely used as an effective method for image segmentation. However, FCM is sensitive to initialization and is easily trapped in local optima. In this paper, several enhanced models for FCM clustering were proposed, namely W_SS_FCM, LAWS_SS_FCM and H_FCM, to promote the performance of standard FCM. The proposed algorithms merge partial supervision with spatial locality to increase conventional FCM’s robustness. A comparison study was conducted to validate the proposed methods’ performance applying well established measures on three datasets. Experimental results show considerable improvement over standard FCM and other variants of the algorithm. It also manifests high robustness against noise attacks.
KeywordsFCM clustering segmentation spatial locality partial supervision
Unable to display preview. Download preview PDF.
- 2.Youssef, S.M., Rizk, M., El-Sherif, M.: Dynamically Adaptive Data Clustering using Intelligent Swarm-like Agents. International Journal of Mathematics and Computing 1, 108–118 (2007)Google Scholar
- 7.Szilagyi, L., Benyo, Z., Szilagyi, S.M., Adam, H.S.: MR Brain Image Segmentation Using an Enhanced Fuzzy C-Means Algorithm. In: 25th International Conference of IEEE EMBS, pp. 17–21 (2003)Google Scholar
- 10.Lim, J.S.: Two-Dimensional Signal and Image Processing. Prentice Hall, Englewood Cliffs (1990)Google Scholar
- 11.Laws, K.I.: Textured image segmentation. University of Southern California, Los Angles, California (1980)Google Scholar