Publication

Abstract : A plethora of magnetic resonance (MR) image segmentation methods exist in the published literature but most of them fail at recognising small regions in MR images accurately due to inefficient segmentation techniques. Through this article, we propose a novel and efficient MRI image segmentation technique which employs an improvised genetic algorithm (GA) based on twin point cross over mutation for automated segmentation. The resultant image from GA is used as an input for social group optimisation technique (SGO), and a lightweight computationally efficient algorithm for refining the segmented image. We have carried out an experiment on benchmark and real time images to compare the proposed technique with the existing segmentation methods which use teacher learner-based optimisation (TLBO). We have observed that proposed approach exhibits better performance over its counterpart.