A novel method for image processing using Particle Swarm Optimization technique

Image segmentation has key influence in numerous medical imaging uses. In this paper, we present a new algorithm for spatial fuzzy segmentation using modified particle swarm optimization of medical & multimedia data. The algorithm is realized by modifying the scaling parameters in the conventional fuzzy C-means (FCM) algorithm using Modified Particle Swarm Optimization (MPSO). Spatial coordinates depend on filter radius, weight, gradient & threshold. Firstly, the initial parameters in the FCM are replaced by optimized parameters, & thus the corresponding algorithm is derived & called as the SFCM-MPSO. Outcomes of the experiment on both real MR images & Multimedia images demonstrate that the proposed algorithms have better performance when noise & other artefacts are present than the standard algorithms. Voxel based error method shows Positive Predictive Value (PPV), Sensitivity (Sens), & Dice Similarity Coefficient (DSC) between existing methodology.