Publication

Abstract : As of now, several improvements have been carried out to increase the performance of previous conventional clustering algorithms for image segmentation. However, most of them tend to have met with unsatisfactory results. In order to overcome some of the drawback like dead centers and trapped centers, in this article presents a new clustering-based segmentation technique that may be able to overcome some of the drawbacks we are passing with conventional clustering algorithms. We named this clustering algorithm as optimized kmeans clustering algorithm for image segmentation. OKM algorithm that can homogenously segment an image into regions of interest with the capability of avoiding the dead centre and trapped centre problems. The robustness of the OKM algorithm can be observed from the qualitative and quantitative analyses.