An Image Registration Method Based upon Information Theorem on Overlapped Region

Abstract:

Digital image and video have been widely applied to many practical applications due to their simple image acquirement. Image registration is an important image processing for integrating information from images. For Image registration, it is intuitive to orientate images by matching corresponding pixels being considered idealistically identical on the overlapping region. Based on this idea, this article proposes an image registration method that applies the information theorem to the corresponding intensity data. An entropy-based objective function is developed upon the histogram of the intensity differences as to evaluate the similarity between images. Intensity differences represent the differences of the corresponding pixels between the referenced and sensed images on the overlapped region. The sensed image is aligned to the referenced image by minimizing the proposed objective function through iteratively updating the parameters of the projective transformation during the optimization process. The experimental results obtained by means of several test image sets illustrate the effectiveness and feasibility of the proposed image registration method.

• Periodical: Applied Mechanics and Materials (Volumes 58-60)
• Pages: 1985-1989
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.58-60.1985
• Online since: June 2011
• Authors: Yu Chiang Chuang, Shu Kai S. Fan
• Keywords: Entropy, Image Registration, Information Theorem, Intensity Difference

References

[1] A. Goshtasby: 2-D and 3-D Image Registration for Medical, Remote Sensing, and Industrial Applications (John Wiley & Sons Inc, 2005).

[2] H. Hanaizumi and S. Fujimura: An automated method for registration of satellite remote sensing images. In Proceedings of the International Geoscience and Remote Sensing Symposium IGARSS'93 (1993), pp.1348-1350.

DOI: 10.1109/igarss.1993.322087

[3] A. Collignon, F. Maes, D. Delaere, P. Vandermeulen, P. Suetens, and G. Marchal: Automated multi-modality image registration based on information theory. Information Process. Med. Imaging (1995).

DOI: 10.1109/mmbia.1996.534053

[4] P. A. Viola, and W. M. Wells: Alignment by maximization of mutual information. 5th Int. Conf. Computer Vision (1995), pp.15-23.

[5] C. Studholme, D. L. G. Hill, and D. J. Hawkes: An overlap invariant entropy measure of 3D medical image alignment. Pattern Recognition, Vol. 32, no. 1 (1999), pp.71-86.

DOI: 10.1016/s0031-3203(98)00091-0

[6] R. Gan, and A.C.S. Chung: Multi-dimensional mutual information based robust image registration using maximum distance-gradient magnitude. IPMI'05, Glenwood Springs, Colorado, USA, Lecture Notes in Computer Science, Vol. 3565 (2005), pp.210-221.

DOI: 10.1007/11505730_18

[7] Y. S. Kim, J. H. Lee, and J. B. Ra: Multi-sensor image registration based on intensity and edge orientation information. Pattern Recognition, Vol. 41, no. 11 (2008), pp.3356-3365.

DOI: 10.1016/j.patcog.2008.04.017

[8] C. Shannon: A mathematical theory of communication. Bell Syst. Tech. J., Vol. 27 (1948), pp.379-423 and pp.623-656, reprinted with correction.

[9] W. H. Press, B. P. Flannery, S. A. Teukolsky, and W. T. Vetterling: Numerical Recipes in C (Cambridge Univ. Press, Cambridge, U.K. 1992).

DOI: 10.1017/s0263574700010675