Data Mining and Knowledge Engineering

P. Rukmini Devi ¹, N. Mohan ², V. Praveen Kumar ³, A. Nageswara Rao ⁴

Affiliations
1 PVP Siddartha Institute of Engineering and Technology, University of JNTUK, IN
2 Pragati Engineering College, University of JNTUK, IN
3 Central University of Hyderabad, IN
4 Dept. CSE, Pragati Engineering College, University of JNTUK, Surampalem, IN

Abstract

This paper presents a variation of Fuzzy c-Means (FCM) algorithm that provides image clustering. The proposed algorithm incorporates the local spatial information and gray level information in a novel fuzzy way. The new algorithm is called C-Means with Fuzzy Local Information (CMFLI). CMFLI can overcome the disadvantages  of known fuzzy c-means algorithm and at the same time enhances the clustering performance. The major characteristic of CMFLI is the use of fuzzy local information (both spatial and gray level) similarity measure, aiming to guarantee noise insensitiveness and image detail preservation. Furthermore, the proposed algorithm is fully free of empirically adjusted parameters (a, λg , λs etc.) incorporated into all other fuzzy c-means algorithms proposed in the literature. Experiments performed on synthetic and real world images show that CMFLI algorithm is efficient,providing robustness to noisy images.

Keywords

Clustering, Fuzzy C-Means, Fuzzy Constraints, Graylevel Constraints, Image Segmentation, Spatial Constraints.

Full Text