SPATIALLY WEIGHTED MUTUAL INFORMATION FOR IMAGE REGISTRATION

被引：1

作者：

Aldrich, Chris ^{[1
]}

Amankwah, Anthony ^{[2
]}

机构：

[1] Curtin Univ, Western Australian Sch Mines, GPO Box U1987, Perth, WA 6845, Australia

[2] Amankwah Consult, POB 10300, Accra, Ghana

来源：

2021 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM IGARSS | 2021年

关键词：

mutual information; weighted mutual information; image registration;

D O I：

10.1109/IGARSS47720.2021.9553987

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

In this paper, we have proposed a new similarity metric for image registration. The similarity metric combines mutual information and a weighting function based on alignability of local regions in images. Experimental results show that the new similarity metric can be superior to mutual information and correlation coefficients.

引用

页码：5429 / 5432

页数：4

共 7 条

[1]

Amankwah A., 2005, P IEEE INT GEOSC REM

[2]

Amankwah A, 2012, 2012 OCEANS

[3]

Ma B., 2000, P IEEE INT C IM PROC

[4] Image registration by maximization of combined mutual information and gradient information [J].