Specifications

Issue: 3
Issue date: 2013
Publication year: 2013
Pages: 250-258
Language: English
ISSN: 20058039
E-ISSN: 22339337
Document type: Journal article (JA)
Publisher: Advanced Institute of Convergence Information Technology, Myoungbo Bldg
3F,, Bumin-dong 1-ga, Seo-gu, Busan, 602-816, Korea, Republic of
Abstract: How to obtain valid fusion coefficients is the key problem in image fusion
processing. In terms of the characters of multispectral images, contrast pyramid (CP) and
contourlets are constructed to filter the images. Furthermore, a kind of evolution computation
idea-immune clonal selection algorithm is introduced into image fusion processing to optimize
the fusion coefficients for better fusion results. Fusion performance is evaluated through
subjective inspection, as well as objective fusion performance measurements. Simulation results
of multispectral images clearly demonstrate the superiority of this new approach. When
compared to conventional wavelets and contourlet systems, Information entropy (IE) values keep
at a high level; average grads (AG) values increase averagely about 2.1 and 1.1, respectively;
standard deviation (STD) values increase averagely about 3.4 and 1.9, respectively; computing
efficiencies increase averagely about 34% and 54%, respectively.
Number of references: 13
Main heading: Image fusion
Controlled terms: Image classification
Uncontrolled terms: Clonal selection - Clonal selection algorithms - Computing
efficiency - Contourlet transform - Contourlets - Evolution computation - Fusion
coefficients - Fusion performance - Image fusion processing - Immune clonal
selections - Information entropy - Multi-spectral image fusions - Multispectral
images - New approaches - Standard deviation
Classification code: 716 Telecommunication; Radar, Radio and Television - 723.2 Data
Processing and Image Processing
DOI: 10.4156/ijact.vol5.issue3.29
Database: Compendex
Compilation and indexing terms, © 2013 Elsevier Inc.
6.
Accession number: 20130816046134
Title: The research on pulsed eddy current in non-destructive testing for metal casing
Authors: Wang, Xue-long1, 3 ; Song, Xi-Jin2 ; Zhang, Jing1/王学龙;;张璟
Author affiliation:
1 School of Computer Science and Engineering, Xi'an University of Technology, China
2 Electronic Engineering School, Xi'an Shiyou University, China
3 School of Computer Science, Xi'an Shiyou University, China
Corresponding author: Song, X. J. ([e-mail])
Source title: Journal of Convergence Information Technology