Uniform discrete curvelet transform for multi-focus image fusion

Yang Yang; Dai Ming; Zhou Luoyu

A novel fusion algorithm for multi-focus images was proposed using Uniform Discrete Curvelet Transform(UDCT) for its characteristics of multi-scale; multi-direction and low redundancy. First, the source images were decomposed into several subbands using UDCT. Then, according to the characteristics of multi-focus images, the coefficients of low-frequency subband were fused with a scheme based on the sum-modified-laplacian; the coefficients of high-frequency subbands were fused with the fusion rule based on local energy; and the consistency of the fused coefficients was verified. Finally, the subband coefficients were reconstructed, and the fused image was obtained. The experiment results indicate that the proposed method can effectively fuse the directional information and detailed features of source images, and suppress pseudo-Gibbs phenomena of fused image; compared with other fusion methods, such as those based on Laplacian pyramid transform, discrete wavelet transform and contourlet transform, this method obtains better fusion quality in terms of both visual and quantified measure.

1. Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun 130033,China;

2. University of Chinese Academy of Sciences,Beijing 100049,China

Received Date: 2013-01-03

Rev Recd Date: 2013-02-15

Publish Date: 2013-09-25

Key words:

Abstract: A novel fusion algorithm for multi-focus images was proposed using Uniform Discrete Curvelet Transform(UDCT) for its characteristics of multi-scale; multi-direction and low redundancy. First, the source images were decomposed into several subbands using UDCT. Then, according to the characteristics of multi-focus images, the coefficients of low-frequency subband were fused with a scheme based on the sum-modified-laplacian; the coefficients of high-frequency subbands were fused with the fusion rule based on local energy; and the consistency of the fused coefficients was verified. Finally, the subband coefficients were reconstructed, and the fused image was obtained. The experiment results indicate that the proposed method can effectively fuse the directional information and detailed features of source images, and suppress pseudo-Gibbs phenomena of fused image; compared with other fusion methods, such as those based on Laplacian pyramid transform, discrete wavelet transform and contourlet transform, this method obtains better fusion quality in terms of both visual and quantified measure.

HTML

Reference (27)

[1]	Guo Lei, Li Huihui, Bao Yunsheng. Image Fusion[M]. Beijing: Publishing House of Electronics Industry Press, 2008. (in Chinese) 郭雷, 李晖晖, 鲍永生. 图像融合[M]. 北京:电子工业出版社, 2008.
[2]
[3]	Xia Mingge, He You, O'Yang Wen, et al. Overview of wavelet-analysis-based image fusion[J]. Infrared and Laser Engineering, 2003, 32(2): 177-181. (in Chinese) 夏明革, 何友, 欧阳文, 等. 基于小波分析的图像融合评述[J]. 红外与激光工程, 2003, 32(2): 177-181.
[4]
[5]
[6]	Truong T. Nguyen, Herv Chauris. uniform discrete curvelet transform[J]. IEEE Transactions on Signal Processing, 2010, 58(7): 3618-3614.
[7]
[8]	Cands E J, Demanet L, Donoho D L, et al. Fast discrete curvelet transforms[J]. Multiscale Modeling and Simulation, 2006, 5(3): 861-899.
[9]	Burt P J, Adelson E H. The Laplacian pyramid as a compact image code[J]. IEEE Transactions on Communications, 1983, 31(4): 532-540.
[10]
[11]
[12]	Mallat S G. A theory for multiresolution signal decomposition: The wavelet representation[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 1989, 11(7): 674-693.
[13]	Do M N, Vetterli M. Contourlet: A directional multiresolution image representation[C]//IEEE International Conference on Image Processing Rochester, 2002: 357-360.
[14]
[15]	Do M N. Directional multiresolution image representations[D]. Lausanne: Switzerland Swiss Federal Institute of Technology, 2001.
[16]
[17]	Nguyen T T, Oraintara S. The shiftable complex directional pyramid, part1: Theoretical aspects[J]. IEEE Trans Signal Process, 2008, 56(10): 4651-4660.
[18]
[19]	Bredlay A P. Shift-invariance in the discrete bwavelet transform[J]. Digital Image Computing: Techniques and Applications, 2003, 10-12.
[20]
[21]
[22]	Huang Wei, Jing Zhongliang, Evaluation of focus measures in multi-focus image fusion[J]. Pattern Recognition Letters, 2007, 28(4): 493-500.
[23]	Qu G, Zhang D, Yan P. Information measure for performance of image fusion[J]. Electronics Letters, 2002, 38(7): 313-315.
[24]
[25]
[26]	Piella G, Heijmans H. A new quality metric for image fusion[C]. Proceeding of IEEE International Conference on Image Processing Barcelona Spain, 2003: 173-176.
[27]	Wang Haihui, Peng Jiaxiong, Wu Wei. Comparison of the methods of evaluating the performance of multi-sensor image fusion[J]. Infrared and Laser Engineering, 2004, 33(02): 189-193. (in Chinese) 王海晖, 彭嘉雄, 吴巍. 评价多传感器图像融合效果方法的比较[J]. 红外与激光工程, 2004, 33(02): 189-193.

Uniform discrete curvelet transform for multi-focus image fusion

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Article Metrics

Related

Proportional views