Intuitionistic fuzzy color clustering of human cell images on different color models

Issue title: Hybrid approaches for approximate reasoning

Article type: Research Article

Authors: Chaira, Tamalika

Affiliations: Centre for Biomedical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, India, E-mail: [email protected]

Abstract: This paper provides a color cell image clustering algorithm using intuitionistic fuzzy set theory using different color models. The clustering algorithm clusters the blood cells very clearly that helps in detecting various types of human diseases. Clustering of medical images is a challenging task as medical images are vague in nature due to poor illumination. So the boundaries or regions are not clear. Clustering using fuzzy set theory is very robust but still there is some uncertainty present while defining the membership function in fuzzy set theory. This uncertainty is due the lack of knowledge or personal error while defining the membership function. Intuitionistic fuzzy set takes into account this uncertainty and thus it may be useful in medical or real time image processing. The two uncertainty parameters in intuitionistic fuzzy set thus help in converging the cluster center to a desirable location than the cluster centers obtained by fuzzy C means algorithm. Different color models e.g., RGB, HSV, and CIELab are used in this algorithm and it is found that RGB and CIELab give almost similar result. The algorithm is also tested on conventional fuzzy C means algorithm to show the efficacy of the new algorithm.

Keywords: Intuitionistic fuzzy set, fuzzy clustering, Yager generator, fuzzy complement, hesitation degree

DOI: 10.3233/IFS-2012-0494

Journal: Journal of Intelligent & Fuzzy Systems, vol. 23, no. 2-3, pp. 43-51, 2012