Application of Swarm Intelligence in Fuzzy Entropy Based Image Segmentation

Abstract

AbstractAn image segmentation technique based on Modified Particle Swarm optimised—fuzzy entropy is applied for Infra Red (IR) images to detect the object of interest and Magnetic Resonance (MR) brain images to detect a brain tumour is presented in this chapter. Adaptive thresholding of input IR images and MR images are performed based on the proposed method. The input image is classified into dark and bright parts with Membership Functions (MF), whose member functions of the fuzzy region are Z-function and S-function. The optimal combination of parameters of these fuzzy MFs are obtained using Modified Particle Swarm Optimization (MPSO) algorithm. The objective function for obtaining the optimal fuzzy MF parameters is considered to be the maximum the fuzzy entropy. Through numerous examples, the performance of the proposed method is compared with those using existing entropy-based object segmentation approaches and the superiority of the proposed method is demonstrated. The experimental results obtained are compared with the enumerative search method and Otsu segmentation technique. The result shows the proposed fuzzy entropy based segmentation method optimized using MPSO achieves maximum entropy with proper segmentation of region of interest for IR images and infected areas for MR brain images with least computational time.KeywordsFuzzy entropyModified particle swarm optimization