A multi-scale contrast-based image quality assessment model for multi-exposure image fusion

摘要

Highlights•Propose a multi-scale contrast-based IQA model for multi-exposure image fusion.•Extract contrast structure and contrast saturation to obtain contrast similarity map.•Compute the weight of each reference image based on its relevance to the MEF image.•Exploit multi-scale scheme to explore image details on MEF quality assessment.•Experimental results justify the accuracy and effectiveness of the proposed method.AbstractIn this paper, an accurate and efficientimage quality assessment(IQA) model using the contrast information, calledmulti-scale contrast-based model(MCM), is proposed for conducting objective quality evaluation ofmulti-exposure image fusion(MEF). It is inspired by the fact that thehuman visual system(HVS) is highly sensitive to contrast that is naturally inherited in the MEF application. The key novelty of the proposed MCM lies in the usage of two salient contrast features, i.e., contrast structure and contrast saturation. For each reference and MEF images, the degree of similarity measured for each above-mentioned contrast attribute is then computed independently, followed by combining them together with the weight of each reference image computed based on its relevance to MEF image for obtainingcontrast similarity maps (CSMs). Subsequently, all the obtained CSMs are fused using a standard deviation pooling strategy to generate the quality score. Finally, a multi-scale scheme is utilized to explore the image details from finer to coarser scales for producing the final MCM score. Simulation results have clearly shown that the proposed MCM model is more consistent with the perception of the HVS on the evaluation of MEF images than multiple state-of-the-art IQA methods.