Image Segmentation Method Based on Fuzzy Entropy and Grey Relational Analysis

Authors:
Yuanyuan Liu;Wenbo Liu;Ziyang Zhen;Gong Zhang
Affiliations:
Nanjing University of Aeronautics and Astronautics, China;Nanjing University of Aeronautics and Astronautics, China;Nanjing University of Aeronautics and Astronautics, China;Nanjing University of Aeronautics and Astronautics, China
Venue:
ICIG '07 Proceedings of the Fourth International Conference on Image and Graphics
Year:
2007

Citing 0
Cited 1

Multi-objective fuzzy clustering method for image segmentation based on variable-length intelligent optimization algorithm

ISICA'10 Proceedings of the 5th international conference on Advances in computation and intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

allusion to the sensitivity towards the noise of the traditional fuzzy entropy method, an improved image segmentation method based on fuzzy entropy and grey relational analysis is proposed in the paper. In this modification, the grey relational degree is introduced to express the degree of the pixels belonging to the object or background accurately. we select the current pixel and its neighborhood pixels as the comparative sequence, and compute the grey relational degree between the comparative sequence and the reference sequence, based on which the membership function of the fuzzy entropy function is redefined in which the membership of the current pixel is determined not only by its own gray value but also by the gray values of its neighborhood pixels. The segmentation experimental results of the Cameraman, MR and Tire images demonstrate the good performance of reducing the noise by the improved method.