Handling Fuzzy Image Clustering with a Modified ABC Algorithm
Salima Ouadfel, Souham Meshoul · International Journal of Intelligent Systems and Applications · 2012
Image segmentation can be cast as a clustering task where the image is partitioned into clusters.Pixels within the same cluster are as homogenous as possible whereas pixels belonging to different clusters are not similar in terms of an appropriate similarity measure.Several clustering methods have been proposed for image seg mentation purpose among wh ich the Fu zzy C-Means clustering algorith m.However this algorith m still suffers fro m some drawbacks, such as local optima and sensitivity to init ialization.Art ificial Bees Co lony algorith m is a recent population-based optimization method which has been successfully used in many complex problems.In this paper, we propose a new fuzzy clustering algorithm based on a modified Artificial Bees Colony algorith m, in which a new mutation strategy inspired from the Differential Evolution is introduced in order to improv e the explo itation process.Experimental results show that our proposed approach imp roves the performance o f the basic fuzzy C-Means clustering algorith m and outperforms other population based optimization methods.