A Registration Method Based on Image Edge Normalized Correlation

Abstract:

In order to solve the infrared and visible image registration problem, a new edge matching method is proposed. Firstly, the algorithm gets edges using Canny operator, and then computes the image edge normalized correlation value (IENC) which is treated as the matching degree of registration. In order to evaluate the performance of the proposed algorithm, a comparison experiment between the proposed algorithm and the algorithm based on Hausdorff distance is done. Experimental results show that the proposed algorithm is effective, small amount of computation and good stability.

• Periodical: Applied Mechanics and Materials (Volumes 241-244)
• Pages: 3092-3097
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.241-244.3092
• Online since: December 2012
• Authors: Lian Fa Bai, Li Qin Zhang, Xin Jing, Jiang Yue
• Keywords: Canny Operator, Edge, Image Edge Normalized Correlation (IENC), Infrared Image, Registration, Visible Image

References

[1] Liang Zong, Yanhui Wu: A Parallel Matching Algorithm Based on Image Gray Scale. In: 2009 International Joint Conference on Computational Sciences and Optimization, pp.109-111. IEEE Press, Sanya (2009).

DOI: 10.1109/cso.2009.131

[2] John Canny: A Computational Approach to Edge Detection. J. IEEE Transactions on Pattern on Pattern Analysis and Machine Intelligence, Vol. 8(6), pp.679-698 (1986).

DOI: 10.1109/tpami.1986.4767851

[3] Jin Gan, Xiaodan Wang, Jie Zhao, Ailing Wang: Fast matching algorithm for images matching based on edge light characteristic. J. Computer Engineering and Applications, Vol. 46(11), pp.193-195 (2010). In Chinese.

[4] Min Xu, Pramod K. Varshney: A Subspace Method for Fourier-Based Image Registration. J. IEEE Geoscience and Remote Sensing Letters, Vol. 6(3), pp.491-494 (2009).

DOI: 10.1109/lgrs.2009.2018705

[5] Guoqiang Ni, Qiong Liu: Analysis and prospect of multi-source image registration techniques. J. Opto-Electronic Engineering, Vol. 31(9), pp.1-6 (2004) . In Chinese.

[6] Lipi Niu, Xiuhua Jiang, Wenhui Zhang, Dongxin Shi: A multi-sensor image registration approach based on long-edge-correlation. In: 2010 3rd IEEE International Conference on Computer Science and Information Technology, Vol. 3, pp.34-38. IEEE Press, Chengdu (2010).

DOI: 10.1109/iccsit.2010.5564808

[7] Jiaqiang Zhong, Runsheng Wang: Image Registration Using Edge-Based Methods. J. Computer Engineering & Science, Vol. 23(6), pp.25-29 (2001) . In Chinese.

[8] Anjun Chen, Wei Chen, Shiyi Mao: An Image Edge Based Algorithm for Multisensor Image Registration. J. Journal of Electronics & Information Technology, Vol. 26(5), pp.679-684 (2004) . In Chinese.

[9] Xiangjie Yang: Adaptive hill climbing and iterative closest point algorithm for multisensor image registration with partial Hausdorff distance. J. SPIE, pp.99-109 (2000).

DOI: 10.1117/12.381623

[10] Jinsha Yuan, Zhenbing Zhao, Qiang Gao, Ying-hui Kong: Review and prospect on infrared/visible image registration. J. Laser & Infrared, Vol. 39(7), pp.693-699 (2009) . In Chinese.

[11] Wuge Su, Zhongxiang Tao, Bo Dong: The Quality Measure for Infrared and Visible Image Fusion Based on the Verge Information. J. Fire Control & Command Control, Vol. 37(1), pp.194-197 (2012) . In Chinese.

[12] Lipi Niu, Xiuhua Jiang, Wenhui Zhang, Dongxin Shi: Image Registration Based on Hausdorff Distance. In: 2010 International Conference on Networking and Information Technology, pp.252-256. IEEE Press, Manila (2010).

DOI: 10.1109/icnit.2010.5508517

[13] JianWei Zhang, GuoQiang Han, Yan Wo. Image registration based on generalized and mean Hausdorff distances[A]. Jian-Wei Zhang. Proceedings of the Fourth International Conference on Machine Learning and Cybernetics, Vol. 8, pp.5117-5121. IEEE Press, Guangzhou (2005).

DOI: 10.1109/icmlc.2005.1527845