Objective quality assessment of image fusion

With the rapid development of image fusion technology, image fusion quality evaluation plays a very important guiding role in selecting or designing image fusion algorithms. Objective image quality assessment is an interesting research subject in the field of image quality assessment. The ideal objective evaluation method is consistent with human perceptual evaluation. The paper gives an overview of existing image fusion quality assessment algorithms. Firstly, basic objective evaluation specifications are presented briefly. Secondly, objective image quality assessment algorithms are classified into 4 categories: based on edge information preservation, based on structural similarity (SSIM), based on information theory and based on contrast. They are introduced with emphasis on their strategies and characteristics. At last, the trends of future research are summarized. Objective image quality assessment considering features of the human visual system or based on specific visual tasks is more and more popular. Quality assessments of no reference image and color fusion image are important development directions in future.