2013 IEEE International Symposium on Multimedia (2010)
Dec. 13, 2010 to Dec. 15, 2010
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ISM.2010.53
In this paper, a modified Fuzzy C-means clustering algorithm is proposed for the segmentation of color images. The modified Fuzzy C-means clustering (FCM) algorithm includes both the local spatial information from neighboring pixels, and the spatial Euclidian distance to the cluster’s center of gravity. This new method increases the accuracy of clustering, and improves the tolerance to noise. It also increases the efficiency by reducing the number of iterations needed to achieve convergence. Experimental results on both artificial and natural images demonstrate the effectiveness and efficiency of this improved method.
Fuzzy C-means, clustering, image processing, segmentation
Christophe Gauge, Sreela Sasi, "Modified Fuzzy C-means Clustering Algorithm with Spatial Distance to Cluster Center of Gravity", 2013 IEEE International Symposium on Multimedia, vol. 00, no. , pp. 308-313, 2010, doi:10.1109/ISM.2010.53