Affine Image Registration Based on Geometric Inference

Abstract:

Image registration is widely used in applications for mapping one image to another. As it is often formulated as a point matching problem, in this paper, a novel method, called the Geometric Inference (GI) algorithm, is proposed for feature point based image registration. Firstly, according to affine distance invariant, the global geometric relationship between collinear correspondences is deduced and used for collinear point matching. Secondly, utilizing affine area invariant, geometric relationship between noncollinear correspondences is inferred and used for noncollinear point matching. Finally, the best affine transformation can be discovered from the correspondences composed of the collinear and noncollinear corresponding point pairs. Experiments on synthesized and real data demonstrate that GI is well-adapt to image registration as it is fast and robust to missing points, outliers, and noise.

• Periodical: Applied Mechanics and Materials (Volumes 427-429)
• Pages: 1610-1613
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.427-429.1610
• Online since: September 2013
• Authors: Xing Wei Yan*, Jie Min Hu, Jun Zhang, Jian Wei Wan
• Keywords: Affine Invariants, Feature Point, Geometric Relationship, Registration

References

[1] F. Meskine, M. C Mezouar, N. A . Taleb. Rigid Image Registration Based on the Nonsubsampled Contourlet Transform and Genetic Algorithms [J]. Sensors, 10, (2010).

DOI: 10.3390/s100908553

[2] W. Pan, K. Qin, Y. Chen. An adaptable-multilayer fractional fourier transform approach for image registration[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence. 31, 3 (2009).

DOI: 10.1109/tpami.2008.83

[3] C. Xing, P. H. Qiu. Intensity based image registration by nonparametric local smoothing[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 33, 10, (2011).

DOI: 10.1109/tpami.2011.26

[4] H. Q Bian, J. B. Su. Feature matching based on geometric constraints in weakly calibrated stereo views of curved scenes[J]. Journal of Systems Engineering and Electronics. 19, 3 , (2008).

DOI: 10.1016/s1004-4132(08)60121-8

[5] J. Zhang. A study on automated image registration based on straight line features[C]. Urban Remote Sensing Joint Event, Shanghai, China. (2009).

DOI: 10.1109/urs.2009.5137503

[6] M. Xia, B. Liu. Image registration by super-curves, [J]. IEEE Transaction on Image Processing. 13, 5, (2004).

[7] W. L. Xu, L. H. Zhang. A geometric reasoning based algorithm for point pattern matching[J]. Science In China (F). 44, 6, (2001).

[8] Y. Lamdan, J. T. Schwatrz, H. J. Wolfson. Affine invariant model-based object recognition[J]. IEEE Transaction on Robotics and Automat., 6, 5, (1990).

DOI: 10.1109/70.62047