Abstract：To solve the problem that the traditional point set non-rigid registration algorithm has low precision and slow convergence speed for complex local deformation data, this paper proposes a robust non-rigid registration algorithm based on local affine registration. The algorithm uses a hierarchical iterative method to complete the non-rigid registration of the point set from coarse to fine. In each iteration, the sub shape point sets and sub target point sets are divided and the shape control points of each sub point set are updated. Then the control point guided affine Iterative Closest Point (ICP) algorithm is used to solve the local affine transformation between the corresponding sub point sets. Next, the local affine transformation obtained by the previous step is used to update the sub data point sets and their shape control point sets. Until the registration error converges, the loop ends and outputs the updated shape point set. Experimental results demonstrate that the accuracy and convergence of the proposed algorithm are greatly improved compared with the traditional point set non-rigid registration algorithms.
ABATE A F, NAPPI M, RICCIO D, et al. 2D and 3D face recognition: A survey[J]. Pattern Recognition Letters, 2007, 28(14): 1885-1906. doi: 10.1016/j.patrec.2006.12.018.
[2]
WU G, KIM M, WANG Q, et al. Hierarchical attribute- guided, symmetric diffeomorphic registration for mr brain images[J]. Human Brain Mapping, 2014, 35(3): 1044-1060. doi: 10.1007/978-3-642-33418-4_12.
[3]
ZHANG C, DU S, LIU J, et al. Robust 3D point set registration using iterative closest point algorithm with bounded rotation angle[J]. Signal Processing, 2016, 120(C): 777-788. doi: 10.1016/j.sigpro.2015.01.021.
[4]
ZHANG L, GAO Y, XIA Y, et al. Representative discovery of structure cues for weakly-supervised image segmentation[J]. IEEE Transactions on Multimedia, 2014, 16(2): 470-479. doi: 10.1109/TMM.2013.2293424.
[5]
JAVADI M S, KADIM Z, WOON H H, et al. An automatic robust image registration algorithm for aerial mapping[J]. International Journal of Image and Graphics, 2015, 15(2): 154-169. doi: 10.1142/S0219467815400021.
[6]
DU S, GUO Y, SANROMA G, et al. Building dynamic population graph for accurate correspondence detection[J]. Medical Image Analysis, 2015, 26(1): 256-267. doi: 10.1016/j. media.2015.10.001.
[7]
BESL P J and MCKAY H D. A method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2): 239-256. doi: 10.1109/34. 121791.
[8]
ZHANG K, LI X, and ZHANG J. A robust point-matching algorithm for remote sensing image registration[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 11(2): 469-473. doi: 10.1109/LGRS.2013.2267771.
[9]
DONG J, PENG Y, YING S, et al. Lietricp: An improvement of trimmed iterative closest point algorithm[J]. Neurocomputing, 2014, 140: 67-76. doi: 10.1016/j.neucom. 2014.03.035.
[10]
BERGSTRÖM P and EDLUND O. Robust registration of surfaces using a refined iterative closest point algorithm with a trust region approach[J]. Numerical Algorithms, 2017, 74(3): 755-779. doi: 10.1007/s11075-016-0170-3.
[11]
AMBERG B, ROMDHANI S, and VETTER T. Optimal step non-rigid ICP algorithms for surface registration[C]. IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, USA, 2007: 1-8.
[12]
KOU Q, YANG Y, DU S, et al. A modified non-rigid ICP algorithm for registration of chromosome images[C]. International Conference on Intelligent Computing, Lanzhou, China, 2016: 503-513.
[13]
MYRONENKO A and SONG X. Point set registration: Coherent point drift[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(12): 2262-2275. doi: 10.1109/TPAMI.2010.46.
[14]
HASANBELLIU E, GIRALDO L S, and PRINCIPE J C. A robust point matching algorithm for non-rigid registration using the Cauchy-Schwarz divergence[C]. IEEE international Workshop on Machine Learning for Signal Processing, Beijing, China, 2011: 1-6.
[15]
CHEN J, MA J, YANG C, et al. Non-rigid point set registration via coherent spatial mapping[J]. Signal Processing, 2015, 106(C): 62-72. doi: 10.1016/j.sigpro.2014.07. 004.
[16]
MA J, ZHAO J, and YUILLE A L. Non-rigid point set registration by preserving global and local structures[J]. IEEE Transactions on Image Processing, 2016, 25(1): 53-64. doi: 10.1109/TIP.2015.2467217.
[17]
HARRIS C. A combined corner and edge detector[C]. Proceedings of Fourth Alvey Vision Conference, Manchester, UK, 1988: 147-151.
[18]
NUCHTER A, LINGEMANN K, and HERTZBERG J. Cached k-d tree search for ICP algorithms[C]. International Conference on 3-d Digital Imaging and Modeling, Montreal, Canada, 2007: 419-426.
[19]
CHEN H and LIN T. An algorithm to build convex hulls for 3-D objects[J]. Journal of the Chinese Institute of Engineers, 2006, 29(6): 945-952. doi: 10.1080/02533839.2006.9671195.
[20]
RODRIGUEZ A and LAIO A. Clustering by fast search and find of density peaks[J]. Science, 2014, 344(6191): 1492-1496. doi: 10.1126/science.1242072.
[21]
LATECKI L J, LAKAMPER R, and ECKHARDT T. Shape descriptors for non-rigid shapes with a single closed contour[C]. IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head Island, USA, 2000: 424-429.
