Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/7442
Title: Channel selection for multispectral color imaging using binary differential evolution
Authors: Shen, HL
Yao, JF
Li, C
Du, X
Shao, SJ
Xin, JH 
Issue Date: 2014
Publisher: Optical Society of America
Source: Applied optics, 2014, v. 53, no. 4, p. 634-642 How to cite?
Journal: Applied optics 
Abstract: In multispectral color imaging, thereis a demand to select are duced number of optimal imaging channels to simultaneously speed up the image acquisition process and keep reflectance reconstruction accuracy. In this paper, the channel selection problem is cast as the binary optimization problem, and is consequently solved using a novel binary differential evolution (DE) algorithm. In the proposed algorithm, we define the mutation operation using a differential table of swapping pairs, and deduce the trial solutions using neighboring self-crossover. In this manner, the binary DE algorithm can well adapt to the channel selection problem. The proposed algorithm is evaluated on the multispectral color imaging system on both synthetic and real data sets. It is verified that high color accuracy is achievable by only using a reduced number of channels using the proposed method. In addition, as binary DE is a global optimization algorithm in nature, it performs better than the traditional sequential channel selection algorithm.
URI: http://hdl.handle.net/10397/7442
ISSN: 1559-128X
EISSN: 2155-3165
DOI: 10.1364/AO.53.000634
Appears in Collections:Journal/Magazine Article

Files in This Item:
File Description SizeFormat 
Shen_Channel_Multispectral_Color.pdf849.92 kBAdobe PDFView/Open
Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

3
Last Week
0
Last month
0
Citations as of Sep 10, 2017

WEB OF SCIENCETM
Citations

3
Last Week
0
Last month
0
Citations as of Sep 15, 2017

Page view(s)

79
Last Week
1
Last month
Checked on Sep 17, 2017

Download(s)

49
Checked on Sep 17, 2017

Google ScholarTM

Check

Altmetric



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