Comparison of Fuzzy and Neuro Fuzzy Image Fusion Techniques and its Applications

TL;DR

This paper compares fuzzy and neuro fuzzy image fusion techniques across various applications, evaluating their performance with multiple quality metrics, and finds neuro fuzzy methods generally outperform fuzzy methods in most cases.

Contribution

It provides a comparative analysis of fuzzy and neuro fuzzy image fusion techniques using diverse quality evaluation indices, highlighting their relative strengths.

Findings

Neuro fuzzy fusion outperforms fuzzy fusion in two test cases.

Fuzzy fusion yields better results in one test case.

Multiple quality metrics used to evaluate fusion performance.

Abstract

Image fusion is the process of integrating multiple images of the same scene into a single fused image to reduce uncertainty and minimizing redundancy while extracting all the useful information from the source images. Image fusion process is required for different applications like medical imaging, remote sensing, medical imaging, machine vision, biometrics and military applications where quality and critical information is required. In this paper, image fusion using fuzzy and neuro fuzzy logic approaches utilized to fuse images from different sensors, in order to enhance visualization. The proposed work further explores comparison between fuzzy based image fusion and neuro fuzzy fusion technique along with quality evaluation indices for image fusion like image quality index, mutual information measure, fusion factor, fusion symmetry, fusion index, root mean square error, peak signal to noise ratio, entropy, correlation coefficient and spatial frequency. Experimental results obtained from fusion process prove that the use of the neuro fuzzy based image fusion approach shows better performance in first two test cases while in the third test case fuzzy based image fusion technique gives better results.