DocumentCode
2631548
Title
The application of BEMD to multi-spectral image fusion
Author
Xu, Xiangnan ; Li, Hua ; Wang, An Na
Author_Institution
Air Force Aviation Univ. of PLA, Beijing
Volume
1
fYear
2007
fDate
2-4 Nov. 2007
Firstpage
448
Lastpage
452
Abstract
Multi-spectral Image Fusion is a new research field in image processing. In this paper, for achieving a better fusion result, a image fusion method based on the intensity-hue-saturation(IHS) Transform and Bidimensional Empirical Mode Decomposition(BEMD) is proposed. Firstly, the multi-spectral image is transformed into IHS component. Secondly, the histogram-matched panchromatic image and intensity component are decomposed into a set of BIMFs respectively by means of BEMD. Thirdly, the new intensity component can be obtained by merging the BIMFs of histogram-matched panchromatic image and intensity component. Finally, the new intensity, hue, and saturation components are transformed back to RGB. Experimental results show that this new method can preserve the spectral information in the fusion image; meanwhile, it can merge the spatial details of the panchromatic image.
Keywords
image colour analysis; image fusion; spectral analysis; statistical analysis; transforms; IHS color space; IHS transform; bidimensional empirical mode decomposition; histogram-matched panchromatic image; image processing; intensity component decomposition; intensity-hue-saturation; multispectral image fusion; Data mining; Digital images; Image analysis; Image fusion; Multispectral imaging; Notice of Violation; Pattern analysis; Pattern recognition; Spatial resolution; Wavelet analysis; BEMD; IHS; Image Fusion;
fLanguage
English
Publisher
ieee
Conference_Titel
Wavelet Analysis and Pattern Recognition, 2007. ICWAPR '07. International Conference on
Conference_Location
Beijing
Print_ISBN
978-1-4244-1065-1
Electronic_ISBN
978-1-4244-1066-8
Type
conf
DOI
10.1109/ICWAPR.2007.4420710
Filename
4420710
Link To Document