Fusion Algorithm of Infrared and TV Image Based on Image Quality Evaluation Method

Abstract:

The main method of Infrared and TV image fusion is based on image transform and fusion rule selection. The study implies that the information quantity of Infrared and TV image has significant effect on the result of fusion. This paper proposes one fusion algorithm of infrared and TV image based on image quality evaluation method. The basic idea of the algorithm is that the whole image or the image areas which contains better quantity of information play a leading role in the fusion process. Firstly, algorithm performs the global quality evaluation of infrared image and TV image, and then selects the corresponding fusion strategy according to the quantity of information. The source image has been divided into the high frequency coefficients and low-frequency coefficients using wavelet transform. Second, algorithm selects the rule of coefficients fusion based on the relative image quality of local regions of the image. The algorithm of this paper avoids the interference of low quality image, makes full use of the area of higher information content and achieves the favorable consistency of the fused image. Experiments demonstrate the effectiveness of the algorithm.

• Periodical: Applied Mechanics and Materials (Volumes 513-517)
• Pages: 570-574
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.513-517.570
• Online since: February 2014
• Authors: Bin Zhou*, Xiao Hui Luo
• Keywords: Consistency, Global Image Quality Evaluation, Image Fusion, Local Image Quality Evaluation

References

[1] L. David, Hall,L. James, linas. An introduction to multisensor data fusion, Proc. of the IEEE 1997, 1, pp: 6-23.

[2] Y.H. Jia, Fusion of Landsat TM and SAR images based on principal component analysis, Remote Sensing Technology and Application, 1998, 13 (1), pp: 46-49.

[3] T. Fechner, G. Godlewski, Optimal fusion of TV and infrared images using artificial neural networks. in Proc. of SPIE on Applications and Science of Artificial Neural Networks. Washington, 1995, 1, pp: 919-925.

DOI: 10.1117/12.205203

[4] S. MASSOUT,Y. SMARA, Comparison of fusion by morphological pyramid and by high pass filtering , Urban Remote Sensing Event, 2009. 1, pp: 1-6.

DOI: 10.1109/urs.2009.5137522

[5] Y.J. Pei,J. Yu,H.Y. Zhou, G.H. Cai , The Improved Wavelet Transform Based Image Fusion Algorithm and The Quality Assessment, 3rd International Congress on Image and Signal Processing (CISP), 2010, 1, pp: 219 - 223.

DOI: 10.1109/cisp.2010.5646674

[6] S. X Xing, X. F Lian, T. H Chen, H.B. Xiao, Image Fusion Method Based on NSCT and RobustnessAnalysis, International Conference on Computer Distributed Control and Intelligent Environmental Monitoring, 2011, pp.346-349.

DOI: 10.1109/cdciem.2011.511

[7] CHEN Zhigang, CHEN Jun. Multi-force image fusion method based on information bottleneck clustering. Computer Engineering and Application, 2010, 46(15), pp: 23-27.

[8] GE Zhirong, WANG Bin, ZHANG Liming. Remote sensing image fusion based on Bayes linear estimation, SCIENCE IN CHINA PRESS 2007, 4(37), pp: 501-513.

[9] Hongxun Yao, Min-Yu Huseh, Guilin Yao, and Yazhou Liu. Image Evaluation Factors . ICIAR 2005, LNCS 3656, pp.255-262.