Priority based pheromone algorithm for image cluster

Clustering task aims at the unsupervised classification of patterns in different groups. Clustering problem has been approached from different disciplines. Many Swarm Intelligence algorithms have been developed to solve numerical and combinatorial problems. Clustering with swarm-based algorithms especially Ant colony algorithm is have been shown better results in a variety of real world application. This paper introduces a new algorithm called Priority Based Pheromone Algorithm (PBPA) belongs to Ant colony System to give better optimal solution for clustering. Concept of this algorithm is to build clusters using three potential values priority value, pheromone and heuristic information. This algorithm is compared with normal Ant colony algorithm, Genetic Algorithm and basic K-means algorithm. Comparison is done by percentage of errors, best fitness (time efficiency) and maximum number of iterations. As compared with above said algorithms, proposed method shows better results.