Fast algorithm for 2D fragment assembly based on partial EMD

Abstract

2D Fragment assembly is an important research topic in computer vision and pattern recognition, and has a wide range of applications such as relic restoration and remote sensing image processing. The key to this problem lies in utilizing contour features or visual cues to find the optimal partial matching. Considering that previous algorithms are weak in predicting the best matching configuration of two neighboring fragments, we suggest using the earth mover’s distance, based on length/property correspondence, to measure the similarity, which potentially matches a point on the first contour to a desirable destination point on the second contour. We further propose a greedy algorithm for 2D fragment assembly by repeatedly assembling two neighboring fragments into a composite one. Experimental results on map-piece assembly and relic restoration show that our algorithm runs fast, is insensitive to noise, and provides a novel solution to the fragment assembly problem.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

References

  1. 1.

    Agathos, A., Pratikakis, I., Papadakis, P., Perantonis, S., Azariadis, P., Sapidis, N.S.: 3d articulated object retrieval using a graph-based representation. Visual Comput. 26(10), 1301–1319 (2009)

    Article  Google Scholar 

  2. 2.

    Alt, H., Buchin, M.: Can we compute the similarity between surfaces? Discret. Comput. Geom. 43, 78–99 (2007)

    Article  MATH  MathSciNet  Google Scholar 

  3. 3.

    Alt, H., Guibas, L.J.: Discrete geometric shapes: matching, interpolation, and approximation. Handb. Comput. Geom. 1, 121–153 (1999)

  4. 4.

    Alt, H., Knauer, C., Wenk, C.: Comparison of distance measures for planar curves. Algorithmica 38(1), 45–58 (2004)

    Article  MATH  MathSciNet  Google Scholar 

  5. 5.

    Altantsetseg, E., Matsuyama, K., Konno, K.: Pairwise matching of 3d fragments using fast fourier transform. Visual Comput. 30(6–8), 929–938 (2014)

    Article  Google Scholar 

  6. 6.

    Ancuti, C., Ancuti, C.O., Bekaert, P.: An efficient two steps algorithm for wide baseline image matching. Visual Comput. 25(5–7), 677–686 (2009)

    Article  Google Scholar 

  7. 7.

    Andaló, F.A., Carneiro, G., Taubin, G., Goldenstein, S., Velho, L.: Automatic reconstruction of ancient portuguese tile panels. IEEE Comput. Graphics Appl. (2016) (accepted)

  8. 8.

    Baxter, L.A., Harche, F.: Note: on the greedy algorithm for optimal assembly. Naval Res. Logistics 39, 833–837 (1992)

    Article  MATH  MathSciNet  Google Scholar 

  9. 9.

    Buchin, K., Buchin, M., Wang, Y.: Exact algorithms for partial curve matching via the fréchet distance. In: ACM-SIAM symposium on discrete algorithms, pp. 645–654 (2009)

  10. 10.

    Chen, B., Pan, X.: Geodesic Fourier descriptor for 2D shape matching. In: International Conference on Embedded Software and Systems Symposia, pp. 447–452 (2008)

  11. 11.

    Cui, M., Femiani, J., Hu, J., Wonka, P., Razdan, A.: Curve matching for open 2D curves. Pattern Recogn. Lett. 30(1), 1–10 (2009)

    Article  Google Scholar 

  12. 12.

    Cui, M., Wonka, P., Razdan, A., Hu, J.: A new image registration scheme based on curvature scale space curve matching. Visual Comput. 23(8), 607–618 (2007)

    Article  Google Scholar 

  13. 13.

    Domokos, C., Kato, Z.: Realigning 2d and 3d object fragments without correspondences. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 1–1 (2016)

    Article  Google Scholar 

  14. 14.

    Driemel, A., Har-Peled, S.: Jaywalking your dog—computing the Fréchet distance with shortcuts. SIAM J. Comput. 42(5), 1830–1866 (2013)

    Article  MATH  MathSciNet  Google Scholar 

  15. 15.

    Dyken, C., Dæhlen, M., Sevaldrud, T.: Simultaneous curve simplification. J. Geogr. Syst. 11(11), 273–289 (2009)

    Article  Google Scholar 

  16. 16.

    Freeman, H., Garder, L.: Apictorial jigsaw puzzles: the computer solution of a problem in pattern recognition. IEEE Trans. Electron. Comput. 13(2), 118–127 (1964)

    Article  Google Scholar 

  17. 17.

    da Gama Leito, H.C., Stolfi, J.: Automatic reassembly of irregular fragments. Univ. of Campinas, Tech. Rep. IC-98-06 (1998)

  18. 18.

    Giguere, M.: Three-dimensional puzzle assembly. US Patent 6015150

  19. 19.

    Goldberg, D., Malon, C., Bern, M.: A global approach to automatic solution of jigsaw puzzles. In: Conf Computational Geometry, pp. 82–87 (2002)

  20. 20.

    Grauman, K., Darrell, T.: Fast contour matching using approximate earth mover’s distance. In: Computer Vision and Pattern Recognition, 2004. CVPR 2004. Proceedings of the 2004 IEEE Computer Society Conference on, vol. 1, pp. I–220–I–227 (2004)

  21. 21.

    Gelfand, N., Pottmann, H. Flöry, S., Hofer, M.: Reassembling fractured objects by geometric matching, ACM Trans. Graphics. (3), 569–578 (2006)

  22. 22.

    Huang, Z., Cohen, F.S.: Affine-invariant B-spline moments for curve matching. IEEE Trans. Image Process. 5(10), 1473–1480 (1996)

    Article  Google Scholar 

  23. 23.

    James, G.M.: Curve alignment by moments. Ann. Appl. Stat. 1(2), 2007 (2008)

    MathSciNet  Google Scholar 

  24. 24.

    Kanezaki, A., Harada, T., Kuniyoshi, Y.: Partial matching of real textured 3d objects using color cubic higher-order local auto-correlation features. Visual Comput. 26(10), 1269–1281 (2010)

    Article  Google Scholar 

  25. 25.

    Khan, M.S., Ayob, A.F.M., Isaacs, A., Ray, T.: A novel evolutionary approach for 2D shape matching based on B-spline modeling. In: IEEE Congress on Evolutionary Computation (CEC), pp. 655–661 (2011)

  26. 26.

    Latecki, L.J., Megalooikonomou, V., Wang, Q., Yu, D.: An elastic partial shape matching technique. Pattern Recogn. 40(11), 3069–3080 (2007)

    Article  MATH  Google Scholar 

  27. 27.

    Liu, H., Latecki, L.J., Liu, W.: A unified curvature definition for regular, polygonal, and digital planar curves. Int. J. Comput. Vision 80(1), 104–124 (2008)

    Article  Google Scholar 

  28. 28.

    Maheshwari, A., Sack, J.R., Shahbaz, K., Zarrabi-Zadeh, H.: Improved algorithms for partial curve matching. Algorithmica 69(3), 641–657 (2014)

    Article  MATH  MathSciNet  Google Scholar 

  29. 29.

    Mccreath, E.: Partial matching of planar polygons under translation and rotation. In: Canadian Conference on Computational Geometry (2008)

  30. 30.

    Miller, J.M., Hoffman, R.L.: Automatic assembly planning with fasteners. In: IEEE International Conference on Robotics and Automation, pp. 69–74 (1989)

  31. 31.

    Min, G.C., Fleck, M.M., Forsyth, D.A.: Jigsaw puzzle solver using shape and color. In: The Fourth International Conference on Signal Processing Proceedings, pp. 877–880 (1998)

  32. 32.

    Gu, P., Yan, X.: CAD-directed automatic assembly sequence planning. Int. J. Prod. Res. 33(11), 3069–3100 (1995)

    Article  MATH  Google Scholar 

  33. 33.

    Pal, A., Shanmugasundaram, K., Memon, N.: Automated reassembly of fragmented images. In: International Conference on Multimedia and Expo, pp. 625–628 (2003)

  34. 34.

    Parikh, D., Sukthankar, R., Chen, T., Chen, M.: Feature-based part retrieval for interactive 3d reassembly. In: IEEE Winter Conference on Applications of Computer Vision, pp. 14–14 (2007)

  35. 35.

    Porrill, J., Pollard, S.: Curve matching and stereo calibration. Image Vis. Comput. 9(1), 45–50 (1991)

    Article  Google Scholar 

  36. 36.

    Richter, F., Ries, C.X., Cebron, N., Lienhart, R.: Learning to reassemble shredded documents. IEEE Trans. Multimedia 15(3), 582–593 (2013)

    Article  Google Scholar 

  37. 37.

    Rubner, Y., Tomasi, C.: Perceptual metrics for image database navigation. Springer International 594 (1999)

  38. 38.

    Rubner, Y., Tomasi, C., Guibas, L.J.: The earth mover’s distance as a metric for image retrieval. Int. J. Comput. Vis. 40(2), 99–121 (2000)

    Article  MATH  Google Scholar 

  39. 39.

    Shirdhonkar, S., Jacobs, D.W.: Approximate earth movers distance in linear time. In: Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on, pp. 1–8. IEEE (2008)

  40. 40.

    Shu, X., Wu, X.J.: A novel contour descriptor for 2D shape matching and its application to image retrieval. Image Vis. Comput. 29(4), 286–294 (2011)

    Article  Google Scholar 

  41. 41.

    Shuralyov, D., Stuerzlinger, W.: A 3D desktop puzzle assembly system. In: 2011 IEEE Symposium on 3D User Interfaces (3DUI), pp. 139–140 (2011)

  42. 42.

    Song, Y., Jin, S.: Matching sequences of salient contour points characterized by voronoi region features. Visual Comput. 28(5), 475–491 (2012)

    Article  Google Scholar 

  43. 43.

    Wang, J., Yu, Z., Zhang, W., Wei, M., Tan, C., Dai, N., Zhang, X.: Robust reconstruction of 2D curves from scattered noisy point data. Comput. Aided Des. 50(3), 27–40 (2014)

    Article  Google Scholar 

  44. 44.

    Wang, X., Hu, J., Zhang, D., Qin, H.: Efficient emd and hilbert spectra computation for 3d geometry processing and analysis via space-filling curve. Visual Comput. 31(6–8), 1135–1145 (2015)

    Article  Google Scholar 

  45. 45.

    Webster, R.W., Lafollette, P.S., Stafford, R.L.: Isthmus critical points for solving jigsaw puzzles in computer vision. IEEE Trans. Syst. Man Cybern. 21(5), 1271–1278 (1991)

    Article  Google Scholar 

  46. 46.

    Wei, G., Xiao-dong, S., Huan-ling, L.: Automatic assembly location method based on particle filter. Comput. Integr. Manuf. Syst. 20(7), 1615–1624 (2014)

    Google Scholar 

  47. 47.

    Xu, C., Liu, J., Tang, X.: 2D shape matching by contour flexibility. IEEE Trans. Pattern Anal. Mach. Intell. 31(1), 180–186 (2009)

    Article  Google Scholar 

  48. 48.

    Zheng, Y.F., Pei, R., Chen, C.: Strategies for automatic assembly of deformable objects. In: IEEE International Conference on Robotics and Automation, pp. 2598–2603 (1991)

Download references

Acknowledgments

We are grateful to the editors and anonymous reviewers for their insightful comments and suggestions. This work is supported by NSF of China (61300168, 61571247, 11226328), NSF of Zhejiang (LZ16F030001, LY13F020018), the Open Research Fund of Zhejiang First-foremost Key Subject (XKXL1521, XKXL1406, XKXL1429), and the International Science and Technology Cooperation Project of Zhejiang (2013C24027).

Author information

Affiliations

Authors

Corresponding author

Correspondence to Shuangmin Chen.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zhang, M., Chen, S., Shu, Z. et al. Fast algorithm for 2D fragment assembly based on partial EMD. Vis Comput 33, 1601–1612 (2017). https://doi.org/10.1007/s00371-016-1303-3

Download citation

Keywords

  • Fragment assembly
  • Partial EMD
  • Contour features
  • Lebesgue measure