Abstract
Image fusion is a well-recognized and a conventional field of image processing. Image fusion provides an efficient way of enhancing and combining pixel-level data resulting in highly informative data for human perception as compared with individual input source data. In this paper, we have demonstrated a comprehensive survey of multi-scale and non-multi-scale decomposition-based image fusion methods in detail. The reference-based and non-reference-based image quality evaluation metrics are summarized together with recent trends in image fusion. Several image fusion applications in various fields have also been reported. It has been stated that though a lot of singular fusion techniques seemed to have given optimum results, the focus of researchers is shifting toward amalgamated or hybrid fusion techniques, which could harness the attributes of both multi-scale and non-multi-scale decomposition methods. Toward the end, the review is concluded with various open challenges for researchers. Thus, the descriptive study in this paper would form basis for stimulating and nurturing advanced research ideas in image fusion.
Highlights
The process of image fusion can be interpreted as to map the state of object, view, abnormality, modality and world into some perceptible lower dimensions [1], [2]
The methods which aims at combing high spectral resolution images and high spatial resolution panchromatic images popularly called as pan-sharpening problem
The results are analysed in terms of QAB/F factor which gives the measurement of the transfer of a feature such as edges, textures and amount of information transferred from the source images to the fused composite image
Summary
The process of image fusion can be interpreted as to map the state of object, view, abnormality, modality and world into some perceptible lower dimensions [1], [2]. Multisensory image fusion has been extensively used in wide number of applications by academic researchers in the fields of mathematics, engineering sciences and physics. These groups of researchers are further classified into defence laboratories, corporate agencies and defence agencies and so on [4], [5]. Image fusion is an extremely important field of application in remote sensing, defect inspection, concealed weapon detection and military surveillance. Another very important type of image fusion is multi-exposure image fusion. In [1] Zhang and Blum gave a set of image fusion methods based on multi-scale decomposition. C.Pohl, Rui Shen, Peter Burt, V.P.S Naidu, B.K Shreyamsha, Subhasis Chaudhuri
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
