Multi-Modality Image Fusion Using the Nonsubsampled Contourlet Transform

Cuiyin LIU; Shu-qing CHEN; Qiao FU

doi:10.1587/transinf.E96.D.2215

Multi-Modality Image Fusion Using the Nonsubsampled Contourlet Transform

Cuiyin LIU, Shu-qing CHEN, Qiao FU

Full Text Views

0

Cite this

Summary :

In this paper, an efficient multi-modal medical image fusion approach is proposed based on local features contrast and bilateral sharpness criterion in nonsubsampled contourlet transform (NSCT) domain. Compared with other multiscale decomposition analysis tools, the nonsubsampled contourlet transform not only can eliminate the “block-effect” and the “pseudo-effect”, but also can represent the source image in multiple direction and capture the geometric structure of source image in transform domain. These advantages of NSCT can, when used in fusion algorithm, help to attain more visual information in fused image and improve the fusion quality. At the same time, in order to improve the robustness of fusion algorithm and to improve the quality of the fused image, two selection rules should be considered. Firstly, a new bilateral sharpness criterion is proposed to select the lowpass coefficient, which exploits both strength and phase coherence. Secondly, a modified SML (sum modified Laplacian) is introduced into the local contrast measurements, which is suitable for human vision system and can extract more useful detailed information from source images. Experimental results demonstrate that the proposed method performs better than the conventional fusion algorithm in terms of both visual quality and objective evaluation criteria.

Publication: IEICE TRANSACTIONS on Information Vol.E96-D No.10 pp.2215-2223

Publication Date: 2013/10/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1587/transinf.E96.D.2215

Type of Manuscript: PAPER

Category: Image Processing and Video Processing

Authors

Cuiyin LIU
  Kunming Univ. of Science and Tech.,Sichuan University,PanZhihua University
Shu-qing CHEN
  Sichuan University,Putian University
Qiao FU
  PanZhihua University

Keyword

image fusion, medical image, nonsubsampled contourlet transform

Cite this

Copy

Cuiyin LIU, Shu-qing CHEN, Qiao FU, "Multi-Modality Image Fusion Using the Nonsubsampled Contourlet Transform" in IEICE TRANSACTIONS on Information, vol. E96-D, no. 10, pp. 2215-2223, October 2013, doi: 10.1587/transinf.E96.D.2215.
Abstract: In this paper, an efficient multi-modal medical image fusion approach is proposed based on local features contrast and bilateral sharpness criterion in nonsubsampled contourlet transform (NSCT) domain. Compared with other multiscale decomposition analysis tools, the nonsubsampled contourlet transform not only can eliminate the “block-effect” and the “pseudo-effect”, but also can represent the source image in multiple direction and capture the geometric structure of source image in transform domain. These advantages of NSCT can, when used in fusion algorithm, help to attain more visual information in fused image and improve the fusion quality. At the same time, in order to improve the robustness of fusion algorithm and to improve the quality of the fused image, two selection rules should be considered. Firstly, a new bilateral sharpness criterion is proposed to select the lowpass coefficient, which exploits both strength and phase coherence. Secondly, a modified SML (sum modified Laplacian) is introduced into the local contrast measurements, which is suitable for human vision system and can extract more useful detailed information from source images. Experimental results demonstrate that the proposed method performs better than the conventional fusion algorithm in terms of both visual quality and objective evaluation criteria.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E96.D.2215/_p

Copy

@ARTICLE{e96-d_10_2215,
author={Cuiyin LIU, Shu-qing CHEN, Qiao FU, },
journal={IEICE TRANSACTIONS on Information},
title={Multi-Modality Image Fusion Using the Nonsubsampled Contourlet Transform},
year={2013},
volume={E96-D},
number={10},
pages={2215-2223},
abstract={In this paper, an efficient multi-modal medical image fusion approach is proposed based on local features contrast and bilateral sharpness criterion in nonsubsampled contourlet transform (NSCT) domain. Compared with other multiscale decomposition analysis tools, the nonsubsampled contourlet transform not only can eliminate the “block-effect” and the “pseudo-effect”, but also can represent the source image in multiple direction and capture the geometric structure of source image in transform domain. These advantages of NSCT can, when used in fusion algorithm, help to attain more visual information in fused image and improve the fusion quality. At the same time, in order to improve the robustness of fusion algorithm and to improve the quality of the fused image, two selection rules should be considered. Firstly, a new bilateral sharpness criterion is proposed to select the lowpass coefficient, which exploits both strength and phase coherence. Secondly, a modified SML (sum modified Laplacian) is introduced into the local contrast measurements, which is suitable for human vision system and can extract more useful detailed information from source images. Experimental results demonstrate that the proposed method performs better than the conventional fusion algorithm in terms of both visual quality and objective evaluation criteria.},
keywords={},
doi={10.1587/transinf.E96.D.2215},
ISSN={1745-1361},
month={October},}

Copy

TY - JOUR
TI - Multi-Modality Image Fusion Using the Nonsubsampled Contourlet Transform
T2 - IEICE TRANSACTIONS on Information
SP - 2215
EP - 2223
AU - Cuiyin LIU
AU - Shu-qing CHEN
AU - Qiao FU
PY - 2013
DO - 10.1587/transinf.E96.D.2215
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E96-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2013
AB - In this paper, an efficient multi-modal medical image fusion approach is proposed based on local features contrast and bilateral sharpness criterion in nonsubsampled contourlet transform (NSCT) domain. Compared with other multiscale decomposition analysis tools, the nonsubsampled contourlet transform not only can eliminate the “block-effect” and the “pseudo-effect”, but also can represent the source image in multiple direction and capture the geometric structure of source image in transform domain. These advantages of NSCT can, when used in fusion algorithm, help to attain more visual information in fused image and improve the fusion quality. At the same time, in order to improve the robustness of fusion algorithm and to improve the quality of the fused image, two selection rules should be considered. Firstly, a new bilateral sharpness criterion is proposed to select the lowpass coefficient, which exploits both strength and phase coherence. Secondly, a modified SML (sum modified Laplacian) is introduced into the local contrast measurements, which is suitable for human vision system and can extract more useful detailed information from source images. Experimental results demonstrate that the proposed method performs better than the conventional fusion algorithm in terms of both visual quality and objective evaluation criteria.
ER -