Abstract
Image fusion is a process of integrating complementary information from multiple imaging sensors and has broad applications in many fields such as remote sensing, medical imaging, military applications and machine vision. In this paper, we present a novel image fusion approach (FT-KPAD) comprising Kernel Principle Component Analysis and Discrete Wavelet Transform. The use of Structural Similarity measure is proposed for adjusting the quality of finally fused image. A newly developed objective image fusion quality evaluation technique, image quality index, is used to evaluate the performance of our fusion algorithm. Experimental results show that it gives promising results as compared to previous methods and performs considerably well across a variety of multi-sensor imaging data.