Improved Particle Swarm Optimization With Spiral Updating Mechanism for Multimodal Image Registration

A modified particle swarm optimization (PSO) algorithm is proposed with a spiral updating mechanism (spiral-PSO) to optimize the balance between exploration and exploitation phases of the standard PSO. The spiral-PSO approach reduces the possibility of the local optima trapping issue during the optimization process. The proposed algorithm has been tested with 23 standard benchmark functions to compare the spiral-PSO with the standard PSO algorithm. The authors report the application of the spiral-PSO for registration of multimodal remote sensing images and compared the registration results with that of the standard PSO. The proposed approach performs successful image registration and provides better optimization of objective functions as compared to conventional PSO.