Enhancement of medical images in an Atanassov's't intuitionistic fuzzy domain using an alternative intuitionistic fuzzy generator with application to image segmentation

Article type: Research Article

Authors: Chaira, Tamalika

Affiliations: Centre for Biomedical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi, India

Note: [] Corresponding author. Tamalika Chaira, Centre for Biomedical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India. E-mail: [email protected]

Abstract: This paper presents a novel approach for intuitionistic fuzzy medical image enhancement using an alternative intuitionistic fuzzy generator and its advantage in segmentation for detecting/extracting abnormal lesions or blood vessels in medical images. The method constructs an intuitionistic fuzzy image using a proposed intuitionistic fuzzy generator that contains a parameter, ‘lambda’. Optimal value of ‘lambda’ is obtained by maximizing intuitionistic fuzzy entropy. Then contrast intensifier is applied to the intuitionistic fuzzy image to obtain an enhanced image. The method shows an improved contrast of vaguely illuminated structures in medical images which has been proved quantitatively and experimentally. Also the enhanced image using the proposed method segments/extracts abnormal lesions or extracts blood vessels almost accurately. Experimental results show that the proposed method performs better than the existing non-fuzzy/fuzzy/Intuitionistic fuzzy methods with respect to enhancement and segmentation.

Keywords: Contrast enhancement, intuitionistic fuzzy set, hesitation degree, intuitionistic fuzzy entropy, segmentation

DOI: 10.3233/IFS-131102

Journal: Journal of Intelligent & Fuzzy Systems, vol. 27, no. 3, pp. 1347-1359, 2014