Feature Level Fusion of Multimodal Images Using Haar Lifting Wavelet Transform

Authors: Sudipta Majumdar, Jayant Bharadwaj

Abstract:

This paper presents feature level image fusion using Haar lifting wavelet transform. Feature fused is edge and boundary information, which is obtained using wavelet transform modulus maxima criteria. Simulation results show the superiority of the result as entropy, gradient, standard deviation are increased for fused image as compared to input images. The proposed methods have the advantages of simplicity of implementation, fast algorithm, perfect reconstruction, and reduced computational complexity. (Computational cost of Haar wavelet is very small as compared to other lifting wavelets.)

Keywords: Lifting wavelet transform, wavelet transform modulus maxima.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1093968

References:

[1] Chetty M. S. Rani and V. Vijayakumar,"Block Based Image Fusion Techniques using Lifting Wavelet Transform and Neural Networks on Medical Images", International Journal of Computer Science and Information Technology and Security, vol. 2.no. 5, October 2012
[2] France Laliberte, Langis Gagnon and Yunlong Sheng, "Registration and Fusion of Retinal Images: An Evaluation Study", IEEE Transactions on Medical Imaging, vol. 2.2, no. 5, May 2003, pp. 661-673.
[3] Youshen Xia and Mohamed S. Kamel, "Novel Cooperative Neural Fusion Algorithms for Image Restoration and Image Fusion", IEEE Transactions on Image Processing, vol. 16, no.2, February 2007, pp. 367-381.
[4] Shruti Gupta, Karthik P. Ramesh, Erik P. Blasch, "Mutual Information Metric Evaluation for PET/MRI Image Fusion" Proc. of IEEE, 2008, pp. 305-311.
[5] Guo-Zhang GenG, Hao Chen Yan-ying Liu, Yan-jie Wang., "Image Fusion Method of 9/7 Wavelet Transform Based Proc. of IEEE, 2008, pp. 522-524.
[6] Hongbo Wu and Yanqiu Xing, "Pixel Based Image Fusion Using Wavelet Transform SPOT and ETM+ Image", Proc. of IEEE, 2010, pp. 936-940.
[7] C. T. Kavitha and C. C hellamuthu, "Multimodal Medical Image Fusion Based on Integer Wavelet Transform and Neuro Fuzzy", Proc. of IEEE 2010, pp.296-300.
[8] Zheng Liu, Erik blasch, Zhiyun Xue, Jiging Zhao, Robert Laganiere and Wei Wu, "Objective Assesment of Multimodal Image Fusion Algorithms for Context Enhancement in Night Visison: A Comparative Study", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 1, January 2012, pp. 94-109.
[9] Haozheng Ren, Yihua Lan and Yong Zhang, "Research of Multi-Focus Image Fusion Based on M-band and Multi Wavelet Transformation", Proc. of IEEE, 2011, pp. 395-398.
[10] Vigit Prabhu, Susanta Mukhopadhyay, "A Multi-Resolution Image Fusion Scheme for 2D Images Based on Wavelet Transform", Proc. of IEEE, 2012.
[11] Sudipta Kor and U. S. Tiwari,"Feature Level Fusion of Multimodal Medical Images in Lifting Wavelet Transform Domain", Proceedings of IEEE, September, 2004, pp.1479-1482.
[12] Ingrid Daubechies and Wim Swelden, "Factoring Wavelet Transfroms into Lifting Steps", J. Fourier Anal. Appl., vol. 4, 1998, pp. 247-269.
[13] Stephen Malalt and Wen Liang Hwang, " Singularity Detection and Processing with Wavelets", IEEE Transactions on Information Theory, vol. 38, no. 2, March 1992, pp. 617-643.