A novel similarity based quality metric for image fusion

被引：58

作者：

Li, Shanshan ^{[1
]}

Hong, Richang ^{[1
]}

Wu, Xiuqing ^{[1
]}

机构：

[1] Univ Sci & Technol China, EEIS Dept, Hefei, Peoples R China

来源：

2008 INTERNATIONAL CONFERENCE ON AUDIO, LANGUAGE AND IMAGE PROCESSING, VOLS 1 AND 2, PROCEEDINGS | 2008年

关键词：

D O I：

10.1109/ICALIP.2008.4589989

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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 psychophysics 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.

引用

页码：167 / 172

页数：6