A new FCM-based algorithm of hydrophobic image segmentation

Authors:
Yang Qiuxia;Tang Liangrui;Qi Bing;Zhang Jing
Affiliations:
Dept. of Electrical and Electronic Engineering, North China Electric Power University, Beijing, China;Dept. of Electrical and Electronic Engineering, North China Electric Power University, Beijing, China;Dept. of Electrical and Electronic Engineering, North China Electric Power University, Beijing, China;Dept. of Electrical and Electronic Engineering, North China Electric Power University, Beijing, China
Venue:
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 3
Year:
2009

Citing 4
Cited 0

Unsupervised Optimal Fuzzy Clustering

IEEE Transactions on Pattern Analysis and Machine Intelligence
Local entropy-based transition region extraction and thresholding

Pattern Recognition Letters
Analysis of the weighting exponent in the FCM

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Validity-guided (re)clustering with applications to image segmentation

IEEE Transactions on Fuzzy Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In order to effectively distinguish the objects from the background, three transition region feature models were taken into account in this paper, including gradient, local complex and local fuzzy variance. Firstly, three transition region feature models were used to distinguish the transition region and the smooth region. Secondly, experimental results signified that every feature models had effects on extracting the objects from the background and each model had some disadvantages on extracting droplets (or watermarks) from hydrophobic images. Finally, these three models were combined together to form the feature domain for Fuzzy Cmeans clustering (FCM), and then the FCM was applied in segmentation of hydrophobic images. Experimental results illustrated that the proposed algorithm has a great application in segmentation of hydrophobic images, for its efficiency in extracting shape information of droplets (or watermarks).