Particle Swarm Optimization-Based Multispectral Image Fusion for Minimizing Spectral Loss

A novel multispectral image fusion technique is proposed which minimizes the spectral loss of fused product using a proper objective function. It is found that the Relative Average Square Error (RASE) is a good choice to be considered as the objective function. A linear combination of multispectral bands is calculated in which the weights are optimized using particle swarm optimization algorithm. Several experimental studies have been conducted on three public domain datasets to show the effectiveness of the proposed approach in comparison with state-of-the-art methods. The objective and visual assessments of the proposed method support the claims provided in this paper.