On ACO-Based Fuzzy Clustering for Image Segmentation

Authors:
Zhiding Yu;Weiyu Yu;Ruobing Zou;Simin Yu
Affiliations:
Department of Electronic & Computer Engineering, the Hong Kong University of Science & Technology, Clear Water Bay, Kowloon, Hong Kong,;School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China 510641;School of Electronic and Information Engineering, South China University of Technology, Guangzhou, China 510641;School of Automation, Guangdong University of Technology, Guangzhou, China 510006
Venue:
ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II
Year:
2009

Citing 4
Cited 1

The dynamics of collective sorting robot-like ants and ant-like robots

Proceedings of the first international conference on simulation of adaptive behavior on From animals to animats
MAX-MIN Ant system

Future Generation Computer Systems
An improved ant colony algorithm for fuzzy clustering in image segmentation

Neurocomputing
Ant colony system: a cooperative learning approach to the traveling salesman problem

IEEE Transactions on Evolutionary Computation

Heuristic Search for Cluster Centroids: An Ant-Based Approach for FCM Initialization

ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Ant Colony Optimization (ACO) is a newly proposed intelligent algorithm for solving discrete optimization problems such as the Travelling Salesman Problem (TSP). In this paper we introduce a novel ACO-based clustering algorithm and exploit its application in image segmentation. Unlike traditional ACO which is mainly based on probabilistic and hard path choosing, the proposed method utilizes a soft and fuzzy scheme. In detail, every pixel in the image is viewed as an ant and the calculation of membership function is based on heuristic and pheromone information on each cluster center. In addition, memberships are modified to include spatial information which can further improve the algorithm performance for image segmentation. Experiments are taken to examine the performance of ACO-based fuzzy clustering algorithm and segmentation results indicate that the proposed approach has the potential of becoming an established clustering method for image segmentation.