Efficient DWT-based fusion techniques using genetic algorithm for optimal parameter estimation

TL;DR

This paper introduces an improved image fusion method combining DWT/UDWT with a modified genetic algorithm for optimal parameter estimation, enhancing image quality and contrast in multi-modality brain images.

Contribution

It presents a scalable, efficient fusion system using a modified GA at feature level, reducing complexity and identifying key source images.

Findings

Enhanced image contrast and information retention

Reduced computational complexity in parameter estimation

Effective fusion across various image sizes

Abstract

Image fusion plays a vital role in medical imaging. Image fusion aims to integrate complementary as well as redundant information from multiple modalities into a single fused image without distortion or loss of information. In this research work, discrete wavelet transform (DWT)and undecimated discrete wavelet transform (UDWT)-based fusion techniques using genetic algorithm (GA)foroptimalparameter(weight)estimationinthefusionprocessareimplemented and analyzed with multi-modality brain images. The lack of shift variance while performing image fusion using DWT is addressed using UDWT. The proposed fusion model uses an efficient, modified GA in DWT and UDWT for optimal parameter estimation, to improve the image quality and contrast. The complexity of the basic GA (pixel level) has been reduced in the modified GA (feature level), by limiting the search space. It is observed from our experiments that fusion using DWT and UDWT techniques with GA for optimal parameter estimation resulted in a better fused image in the aspects of retaining the information and contrast without error, both in human perception as well as evaluation using objective metrics. The contributions of this research work are (1) reduced time and space complexity in estimating the weight values using GA for fusion (2) system is scalable for input image of any size with similar time complexity, owing to feature level GA implementation and (3) identification of source image that contributes more to the fused image, from the weight values estimated.