Journal of Systems Engineering and Electronics ›› 2012, Vol. 34 ›› Issue (5): 871-875.doi: 10.3969/j.issn.1001-506X.2012.05.03

Previous Articles     Next Articles

 Novel quality metric for infrared and visible image fusion

WANG Xiao-wen1, ZHAO Zong-gui2, TANG Lei3   

  1. 1. Institute of Command and Automation, PLA University of Science and Technology, Nanjing 210007, China；
    2. The 28th Institute, China Electronics Technology Group Corporation, Nanjing 210007, China；
    3. Operation Research Center, Nanjing Army Command College, Nanjing 210045, China
  • Online:2012-05-23 Published:2010-01-03

PDF (PC)

Abstract:

Based on the region partition and association of source images, two regional features of source images are defined  according to the imaging characteristics of infrared and visible images and the requirements of fusion tasks. A regional  similarity assessment index with the regional features and the information entropy and mutual information of fused images  and source images is constructed. A novel nonreference quality evaluation metric for infrared and visible image fusion  is proposed. Experimental results show that this metric fits the results of human visual inspection better than the  recent state of the art image fusion evaluation metrics.

[an error occurred while processing this directive]