Quality Evaluation Measures of Pixel - Level Image Fusion Using Fuzzy Logic

Abstract

Image fusion is a technique to combine the registered images to increase the spatial resolution of acquired low detail multi-sensor images and preserving their spectral information. In fusing panchromatic and multispectral images, the objective is to reduce uncertainty and minimize redundancy in the output while maximizing relevant information. Different fusion methods provide different results for different applications, medical imaging, automatic target guidance system, remote sensing, machine vision, automatic change detection, and biometrics. In this paper, we utilize a fuzzy logic approach to fuse images from different sensors, in order to enhance visualization. The work here further explores the comparison between image fusion using wavelet transform and fuzzy logic approach along with performance/quality evaluation measures like image quality index, entropy, mutual information measure, root mean square error, peak signal to noise ratio, fusion factor, fusion symmetry and fusion index. Experimental results prove that the use of the proposed method can efficiently preserve the spectral information while improving the spatial resolution of the remote sensing images.