Multi-hyperbolic tangent fuzzy c-means algorithm with spatial information for MRI segmentation. (2016)

• Record Type: Journal Article
• Authors: Venu, Nookala; Anuradha, B.
• Is Part Of: International journal of signal and imaging systems engineering. Volume 9:Number 3(2016)
• Page Start: 135
• Page End: 145
• Publication Date: 2016
• Subjects: image segmentation -- fuzzy c-means clustering -- fuzzy logic -- hyperbolic tangent function -- spatial information -- MRI segmentation -- magnetic resonance imaging -- medical images; Signal processing -- Periodicals; Imaging systems -- Periodicals; Information theory -- Periodicals; 621.3822
• Languages: English
• ISSNs: 1748-0698

Abstract

This paper proposes a novel image segmentation using Multi-Hyperbolic Tangent Fuzzy C-Means (HTFCM) algorithm, with spatial information for medical image segmentation. The proposed method uses two hyperbolic tangent functions with the spatial information of neighbouring pixels for clustering of images. The performance of the proposed algorithm is tested on OASIS-MRI image data set. The performance is tested in terms of score, number of iterations (NI) and execution time (TM) under different Gaussian and salt & pepper noises on OASIS-MRI data set. The results after investigating the proposed method show a significant improvement as compared to other existing methods in terms of score, NI and TM under different Gaussian and salt & pepper noises on OASIS-MRI data set.