1 简介
A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement。
Abstract—Low-light images are not conducive to human observation and computer vision algorithms due to their lowvisibility. Although many image enhancement techniques havebeen proposed to solve this problem, existing methods inevitablyintroduce contrast under- and over-enhancement. Inspired by human visual system, we design a multi-exposure fusion frameworkfor low-light image enhancement. Based on the framework, wepropose a dual-exposure fusion algorithm to provide an accuratecontrast and lightness enhancement. Specififically, we fifirst designthe weight matrix for image fusion using illumination estimationtechniques. Then we introduce our camera response model tosynthesize multi-exposure images. Next, we fifind the best exposureratio so that the synthetic image is well-exposed in the regionswhere the original image is under-exposed. Finally, the enhancedresult is obtained by fusing the input image and the syntheticimage according to the weight matrix. Experiments show thatour method can obtain results with less contrast and lightnessdistortion compared to that of several state-of-the-art methods.
2 部分代码
% specify datasets
dataset = {'VV' 'LIME' 'NPE' 'NPE-ex1' 'NPE-ex2' 'NPE-ex3' 'MEF' 'DICM'};dataset = strcat('data', filesep, dataset, filesep, '*.*');% specify methods and metrics
method = {@multiscaleRetinex @dong @npe @lime @mf @srie @BIMEF};metric = {@loe100x100 @vif};for d = dataset, data = d{1};data,
Test = TestImage(data);
Test.Method = method;
Test.Metric = metric;
% run test and display results
Test,
% save test to a .csv file
save(Test);
end
3 仿真结果
4 参考文献
[1] Ying, Z. , L. Ge , and G. Wen . "A Bio-Inspired Multi-Exposure Fusion Framework for Low-light Image Enhancement." (2017).
部分理论引用网络文献，若有侵权联系博主删除。
