Title: An empirical analysis of colour image segmentation using fuzzy c-means clustering

Authors: C.P. Lim, W.S. Ooi

Addresses: School of Electrical and Electronic Engineering, University of Science Malaysia, Engineering Campus, 14300 Nibong Tebal, Penang, Malaysia. ' School of Electrical and Electronic Engineering, University of Science Malaysia, Engineering Campus, 14300 Nibong Tebal, Penang, Malaysia

Abstract: In this paper, an empirical analysis to examine the effects of image segmentation with different colour models using the fuzzy c-means (FCM) clustering algorithm is conducted. A qualitative evaluation method based on human perceptual judgement is used. Two sets of complex images, i.e., outdoor scenes and satellite imagery, are used for demonstration. These images are employed to examine the characteristics of image segmentation using FCM with eight different colour models. The results obtained from the experimental study are compared and analysed. It is found that the CIELAB colour model yields the best outcomes in colour image segmentation with FCM.

Keywords: image segmentation; fuzzy c-means clustering; colour models; pixel clustering; CIELAB; colour images; human perception; human judgement; outdoor scenes; satellite imagery.

DOI: 10.1504/IJKESDP.2010.030469

International Journal of Knowledge Engineering and Soft Data Paradigms, 2010 Vol.2 No.1, pp.97 - 106

Available online: 17 Dec 2009 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article