IEEE Trans Image Process. 2015 Sep;24(9):2712-24. doi: 10.1109/TIP.2015.2428051. Epub 2015 Apr 29.
There has been a growing interest in image fusion technologies, but how to objectively evaluate the quality of fused images has not been fully understood. Here, we propose a method for objective quality assessment of multiexposure multifocus image fusion based on the evaluation of three key factors of fused image quality: 1) contrast preservation; 2) sharpness; and 3) structure preservation. Subjective experiments are conducted to create an image fusion database, based on which, performance evaluation shows that the proposed fusion quality index correlates well with subjective scores, and gives a significant improvement over the existing fusion quality measures.
人们对图像融合技术越来越感兴趣，但如何客观地评估融合图像的质量还没有被充分理解。在这里，我们提出了一种基于评估融合图像质量的三个关键因素的多曝光多聚焦图像融合的客观质量评估方法：1）对比度保持；2）锐度；3）结构保持。通过主观实验创建了一个图像融合数据库，基于该数据库的性能评估表明，所提出的融合质量指标与主观评分有很好的相关性，并优于现有的融合质量度量。
