A New PSO Based Kernel Clustering Method for Image Segmentation

In this paper a novel kernel clustering method is proposed. The application of the proposed clustering algorithm to the problem of unsupervised classification and image segmentation task is investigated. The proposed method provides a new scheme for classifying objects of one data set without any prior knowledge on the number of naturally occurring regions in the data or an assumption on clusters shapes. It´s based on the use of Particle Swarm Optimization (PSO) algorithm and the use of core set concept which is commonly used to resolve the Minimum Enclosing Ball (MEB) problem. The performance of the proposed method has been compared with a few state of the art kernel clustering methods over a test of artificial data and the Berkeley image segmentation dataset.