A Novel Similarity Based Quality Metric for Image Fusion
A new objective non-reference quality metric for the performance of pixel level image fusion is proposed in this paper. The novel metric employs a luminance model that is widely used in visual psychophys-ics and a new contrast model which correlates better with human visual sensitivity to calculate the similarity between fused image and the sources. Experiments show that the metric is effective and compliant with subjective evaluations compared with other metrics.
Shanshan Li Richang Hong Xiuqing Wu
EEIS Department,University of Science and Technology of China
国际会议
2008 International Conference on Audio，Language and Image Processing(2008国际声音、语言、图像过程大会)
镇江
英文
167-172
2008-07-07（万方平台首次上网日期，不代表论文的发表时间）