By Topic

Comparative Study of Clustering Based Colour Image Segmentation Techniques

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Samira Chebbout ; Dept. of Comput. Sci., Larbi Ben M''Hidi Univ., Oum El Bouaghi, Algeria ; Hayet Farida Merouani

Image segmentation is very essential and critical to image processing and pattern recognition. Various clustering based segmentation methods have been proposed. However, it is very difficult to choose the method best suited to the type of data. Therefore, the objective of this research was to compare the effectiveness of three clustering methods involving RGB, HSV and CIE L*a*b* color spaces and a variety of real color images. The methods were: K-means clustering algorithm, Partitioning Around Medoids method (PAM) and Kohonen's Self-Organizing Maps method (SOM). To evaluate these three techniques, the connectivity(C), the Dunn index (D) and the silhouette width (S) cluster validation techniques were used. For C, a lower value indicates a better technique and for D and S, a higher value indicates a better technique. Clustering algorithms were evaluated on natural images and their performance is compared. Results demonstrate that K-means and SOM were considered to be the most suitable techniques for image segmentation among CIE L*a*b* and HSV colour spaces.

Published in:

Signal Image Technology and Internet Based Systems (SITIS), 2012 Eighth International Conference on

Date of Conference:

25-29 Nov. 2012