Unsupervised Image Segmentation Using a Colony of Cooperating Ants
In this paper, we present a novel method for unsupervised image segmentation. Image segmentation is cast as a clustering problem, which aims to partition a given set of pixels into a number of homogenous clusters, based on a similarity criterion. The clustering problem is a difficult optimization problem for two main reasons: first the search space of the optimization is too large, second the clustering objective function is typically non convex and thus may exhibit a large number of local minima. Ant Colony Optimization is a recent multi-agent approach based on artificial ants for solving hard combinatorial optimization problems. We propose the use of the Max-Min Ant System (MMAS) to solve the clustering problem in the field of image segmentation. Each pixel within the image is mapped to its closest cluster taking into account its immediate neighborhood. The obtained results are encouraging and prove the feasibility of the proposed algorithm.
KeywordsImage Segmentation Clustering Ant Colony Optimization Max-Min Ant System
Unable to display preview. Download preview PDF.
- A.k. Jain, M. Murty and P. Flynn. ≪Data Clustering, A Review≫. ACM Computing Survey. Vol. 31, N° 3. 1999.Google Scholar
- T. Stutzle and H. Hoos. ≪ Improvement on Ant System: Introducing the MAX-MIN Ant System≫. In the proceeding of the International Conference on Artificial Neural Networks and Genetic Algorithms, pp: 245–249. Springer-Verlag, Wien, 1997.Google Scholar
- T. Stutzle and H. Hoos. ≪ MAX-MIN Ant System and Local Search for Combinatorial Optimization Problems. Towards Adaptive Tools for Combinatorial Global Optimization≫. 2nd Metaheuristics International Conference, Sophia-Antipolis, France.1997.Google Scholar