UM  > 科技學院  > 電腦及資訊科學系
Neighborhood distance and its application in image fusion
HENG-JUN ZHAO1; ZHAO-WEI SHANG1; BIN FANG1; YUAN-YAN TANG2
2012-10-29
Conference Name2012 International Conference on Wavelet Analysis and Pattern Recognition
Source PublicationProceedings of the 2012 International Conference on Wavelet Analysis and Pattern Recognition
Pages100-105
Conference Date15-17 July 2012
Conference PlaceXian
CountryChina
PublisherIEEE
Abstract

In this paper, we propose the directional neighborhood distance and all-directional neighborhood distance (ADND) to measure the gray value variation between pixels in specific and all direction. The all-directional neighborhood distance is used to fuse multi-source images, and our experiments show that the proposed fusion method is effective in term of some objective evaluation indexes, such as spatial frequency, average gradient, etc. 

KeywordDirectional Neighborhood Distance Image Fusion Image Surface Curvature
DOIhttps://doi.org/10.1109/ICWAPR.2012.6294762
URLView the original
Indexed BySCI
Language英语
Fulltext Access
Citation statistics
Document TypeConference paper
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Affiliation1.College of Computer Science, Chongqing University, Chongqing, 40030, China
2.omputer aDepartment of Cnd Information Science, University of Macau, Macau, China
Recommended Citation
GB/T 7714
HENG-JUN ZHAO,ZHAO-WEI SHANG,BIN FANG,et al. Neighborhood distance and its application in image fusion[C]:IEEE,2012:100-105.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[HENG-JUN ZHAO]'s Articles
[ZHAO-WEI SHANG]'s Articles
[BIN FANG]'s Articles
Baidu academic
Similar articles in Baidu academic
[HENG-JUN ZHAO]'s Articles
[ZHAO-WEI SHANG]'s Articles
[BIN FANG]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[HENG-JUN ZHAO]'s Articles
[ZHAO-WEI SHANG]'s Articles
[BIN FANG]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.