A novel similarity based quality metric for image fusion

被引:360
作者
Yang, Cui [1 ]
Zhang, Jian-Qi [1 ]
Wang, Xiao-Rui [1 ]
Liu, Xin [1 ]
机构
[1] Xidian Univ, Sch Tech Phys, Xian 710071, Peoples R China
基金
高等学校博士学科点专项科研基金; 中国国家自然科学基金;
关键词
image fusion; objective performance evaluation; structural similarity;
D O I
10.1016/j.inffus.2006.09.001
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A novel objective quality metric for image fusion is presented. The interest of our metric lies in the fact that the redundant regions and the complementary/conflicting regions are treated respectively according to the structural similarity between the source images, The experiments show that the proposed measure is consistent with human visual evaluations and can be applied to evaluate image fusion schemes that are not performed at the same level. (c) 2006 Elsevier B.V. All rights reserved.
引用
收藏
页码:156 / 160
页数:5
相关论文
共 11 条
[1]   A Global Quality Measurement of Pan-Sharpened Multispectral Imagery [J].
Alparone, Luciano ;
Baronti, Stefano ;
Garzelli, Andrea ;
Nencini, Filippo .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2004, 1 (04) :313-317
[2]  
BURT P, 1983, IEEE T COMMUN, V4, P532
[3]  
Cvejic N., 2005, Int. J. Signal Process., V2, P178
[4]  
LI H, 1994, P IEEE INT C IM PROC, V1, P51
[5]  
PIELLA G, 2004, P 7 INT C INF FUS ST, P542
[6]   Information measure for performance of image fusion [J].
Qu, GH ;
Zhang, DL ;
Yan, PF .
ELECTRONICS LETTERS, 2002, 38 (07) :313-315
[7]   Perceptual evaluation of different image fusion schemes [J].
Toet, A ;
Franken, EM .
DISPLAYS, 2003, 24 (01) :25-37
[8]   IMAGE FUSION BY A RATIO OF LOW-PASS PYRAMID [J].
TOET, A .
PATTERN RECOGNITION LETTERS, 1989, 9 (04) :245-253
[9]   Image quality assessment: From error visibility to structural similarity [J].
Wang, Z ;
Bovik, AC ;
Sheikh, HR ;
Simoncelli, EP .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2004, 13 (04) :600-612
[10]   Objective image fusion performance measure [J].
Xydeas, CS ;
Petrovic, V .
ELECTRONICS LETTERS, 2000, 36 (04) :308-309