2D registration based on contour matching for partial matching images

Abstract

The mean Hausdorff distance, though highly applicable in image registration, does not work well on partial matching images. An improvement upon traditional Hausdorff-distance-based image registration method is proposed, which consists of the following two aspects. One is to estimate transformation parameters between two images from the distributions of geometric property differences instead of establishing explicit feature correspondences. This procedure is treated as the pre-registration. The other aspect is that mean Hausdorff distance computation is replaced with the analysis of the second difference of generalized Hausdorff distance so as to eliminate the redundant points. Experimental results show that our registration method outperforms the method based on mean Hausdorff distance. The registration errors are noticeably reduced in the partial matching images.

Keywords

image registration / generalized Hausdorff distance / partial matching image

References

[1] ZitovaB, FlusserJ. Image registration methods: A survey [J]. Image and Vision Computing, 2003, 21(11): 977-1000

[2] HanF-f, YangJ-z, LiuYang. Research on preprocessing algorithm for PET-CT image registration [C]. Proceedings of Int Conf on Optoelectronics and Image Processing, 2010, Haiko, China, ICOIP: 266-269

[3] GholipourA, KehtarnavazN, BriggsR, DevousM, GopinathK. Brain functional localization: A survey of image registration techniques [J]. IEEE Trans Medical Imaging, 2007, 26(4): 427-451

[4] BilodeauG A, TorabiA, MorinF. Visible and infrared image registration using trajectories and composite foreground images [J]. Image and Vision Computing, 2011, 29(1): 41-50

[5] WangZ-b, MaY-d, GuJason. Multi-focus image fusion using PCNN [J]. Pattern Recognition, 2010, 43(6): 2003-2016

[6] KimY S, LeeJ H, RaJ B. Multi-sensor image registration based on intensity and edge orientation information [J]. Pattern Recognition, 2008, 41(11): 3356-3365

[7] LiH, PengY-h, LiD-w, XuJ-hua. A new multiresolution medical image registration algorithm based on intensity and edge information [C]. Proceedings of 4th Int Conf on Natural Computation, 2008, Jinan, China, ICNC: 13-17

[8] TangJ-h, YangX, LiuC, WuX-qing. Image registration based on fitted straight lines of edges [C]. Proceedings of 6th World Congress on Intelligent Control and Automation, 2006, Dalian, China, ICA: 9782-9785

[9] LuG, YanJ, KouY, ZhangJ. Image registration based on criteria of feature point pair mutual information [J]. IET Image Processing, 2011, 5(6): 560-566

[10] HuttenlocherD P, KlandermanG A, RucklidgeW J. Comparing images using the Hausdorff distance under translation [C]. Proceedings of IEEE Computer Society Conf on Computer Vision and Pattern Recognition, 1992, Champaign, USA, IEEE: 654-656

[11] TanH-c, ZhangY-jin. Computing Eigenface from edge images for face recognition based on Hausdorff distance [C]. Proceedings of 4th Int Conf on Image and Graphics, 2007, Chengdu, China, ICIG: 639-644

[12] GastaldoP, ZuninoP. Hausdorff distance for target detection [C]. IEEE International Symposium on Circuits and Systems, 2002, Scottsdale, USA, IEEE: 661-664

[13] ShaoF, CaiS-m, GuJ-zheng. A modified Hausdorff distance based algorithm for 2-dimensional spatial trajectory matching [C]. Proceedings of 5th Int. Conf. on Computer Science and Education, 2010, Heifei, China, ICCSE: 166-172

[14] BorgeforsG. Hierarchical chamfer matching: A parametric edge matching algorithm [J]. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1988, 10(6): 849-865

[15] BarrowH G, TenenbaumJ M, BollesR C, WolfH C. Parametric correspondence and chamfer matching: Two new techniques for image matching [C]. Proceedings of 5th Int Joint Conf on Artificial Intelligence, 1977, Cambridge, Massachusetts, JCAZ: 659-663

[16] NiuL-p, JiangX-h, ZhangW-h, ShiD-xin. Image registration based on Hausdorff distance [C]. Proceedings of Int Conf on Networking and Information Technology, 2010, Manila, Philippines, ICNIT: 252-256

[17] WangA, SunX-y, ZhouX-xing. Difference squared Hausdorff distance based medical image registration [C]. Proceedings of Control and Decision Conference, 2011, Guiyang, China, CSC: 4270-4272

[18] XiaM-h, LiuBede. Image registration by “Super-Curves” [J]. IEEE Trans on Image Processing, 2004, 13(5): 720-732

[19] GovinduV, ShekharC. Alignment using distributions of local geometric properties [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1999, 21(10): 1031-1043

[20] HuttenlocherD P, KlandermanG A, RucklidgeW J. Comparing images using the Hausdorff distance [J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1993, 15(9): 850-863

[21] XuH-f, YounisA A. Automatic moving object extraction for content-based applications [J]. IEEE Trans on Circuits and Systems for Video Technology, 2004, 14(6): 796-812

[22] ZhangJ-w, HanG-q, WoYan. Image registration based on generalized and mean Hausdorff distances [C]. Proceedings of Int Conf on Machine Learning and Cybernetics, 2005, Guangzhou, China, ICMLC: 5117-5121