An ICA-based image fusion scheme using only source images

Yin Lu; Fuxiang Wang; Xiaoyan Luo; Jun Zhang

doi:10.1007/978-3-642-26001-8_76

An ICA-based image fusion scheme using only source images

Yin Lu^*, Fuxiang Wang, Xiaoyan Luo, Jun Zhang

^*Corresponding author for this work

Beihang University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In this paper, we propose an image fusion scheme based on Independent Component Analysis (ICA), in which the ICA bases are trained from only source images. For traditional ICA-based image fusion algorithms, a number of sample images similar to source images are required to train the ICA bases. However, it is a difficult task to find such similar training images in practice. Since the image patches have intra-redundancy in one image and inter-similarity in source images, we select patches with representative characteristics of source images to train the ICA bases. Simulation results show that the proposed scheme preserves more information of source images and outperforms previous ICA-based image fusion methods.

Original language	English
Title of host publication	Advances in Information Technology and Industry Applications
Pages	589-596
Number of pages	8
DOIs	https://doi.org/10.1007/978-3-642-26001-8_76
Publication status	Published - 2012
Externally published	Yes
Event	2nd International Conference of Electrical and Electronics Engineering, ICEEE 2011 - Macau, China Duration: 1 Dec 2011 → 2 Dec 2011

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	136 LNEE
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	2nd International Conference of Electrical and Electronics Engineering, ICEEE 2011
Country/Territory	China
City	Macau
Period	1/12/11 → 2/12/11

Keywords

Independent Component Analysis
image fusion
image patch

Access to Document

10.1007/978-3-642-26001-8_76

Cite this

@inproceedings{d329d7f388394e5db94d417b4a660017,

title = "An ICA-based image fusion scheme using only source images",

abstract = "In this paper, we propose an image fusion scheme based on Independent Component Analysis (ICA), in which the ICA bases are trained from only source images. For traditional ICA-based image fusion algorithms, a number of sample images similar to source images are required to train the ICA bases. However, it is a difficult task to find such similar training images in practice. Since the image patches have intra-redundancy in one image and inter-similarity in source images, we select patches with representative characteristics of source images to train the ICA bases. Simulation results show that the proposed scheme preserves more information of source images and outperforms previous ICA-based image fusion methods.",

keywords = "Independent Component Analysis, image fusion, image patch",

author = "Yin Lu and Fuxiang Wang and Xiaoyan Luo and Jun Zhang",

year = "2012",

doi = "10.1007/978-3-642-26001-8_76",

language = "English",

isbn = "9783642260001",

series = "Lecture Notes in Electrical Engineering",

pages = "589--596",

booktitle = "Advances in Information Technology and Industry Applications",

note = "2nd International Conference of Electrical and Electronics Engineering, ICEEE 2011 ; Conference date: 01-12-2011 Through 02-12-2011",

}

Lu, Y, Wang, F, Luo, X & Zhang, J 2012, An ICA-based image fusion scheme using only source images. in Advances in Information Technology and Industry Applications. Lecture Notes in Electrical Engineering, vol. 136 LNEE, pp. 589-596, 2nd International Conference of Electrical and Electronics Engineering, ICEEE 2011, Macau, China, 1/12/11. https://doi.org/10.1007/978-3-642-26001-8_76

TY - GEN

T1 - An ICA-based image fusion scheme using only source images

AU - Lu, Yin

AU - Wang, Fuxiang

AU - Luo, Xiaoyan

AU - Zhang, Jun

PY - 2012

Y1 - 2012

N2 - In this paper, we propose an image fusion scheme based on Independent Component Analysis (ICA), in which the ICA bases are trained from only source images. For traditional ICA-based image fusion algorithms, a number of sample images similar to source images are required to train the ICA bases. However, it is a difficult task to find such similar training images in practice. Since the image patches have intra-redundancy in one image and inter-similarity in source images, we select patches with representative characteristics of source images to train the ICA bases. Simulation results show that the proposed scheme preserves more information of source images and outperforms previous ICA-based image fusion methods.

AB - In this paper, we propose an image fusion scheme based on Independent Component Analysis (ICA), in which the ICA bases are trained from only source images. For traditional ICA-based image fusion algorithms, a number of sample images similar to source images are required to train the ICA bases. However, it is a difficult task to find such similar training images in practice. Since the image patches have intra-redundancy in one image and inter-similarity in source images, we select patches with representative characteristics of source images to train the ICA bases. Simulation results show that the proposed scheme preserves more information of source images and outperforms previous ICA-based image fusion methods.

KW - Independent Component Analysis

KW - image fusion

KW - image patch

UR - http://www.scopus.com/inward/record.url?scp=84862953323&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-26001-8_76

DO - 10.1007/978-3-642-26001-8_76

M3 - Conference contribution

AN - SCOPUS:84862953323

SN - 9783642260001

T3 - Lecture Notes in Electrical Engineering

SP - 589

EP - 596

BT - Advances in Information Technology and Industry Applications

T2 - 2nd International Conference of Electrical and Electronics Engineering, ICEEE 2011

Y2 - 1 December 2011 through 2 December 2011

ER -

An ICA-based image fusion scheme using only source images

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this