Machine Vision and Applications

, Volume 29, Issue 4, pp 553–572 | Cite as

Adaptive locally affine-invariant shape matching

  • Smit Marvaniya
  • Raj Gupta
  • Anurag Mittal
Original Paper


Matching deformable objects using their shapes are an important problem in computer vision since shape is perhaps the most distinguishable characteristic of an object. The problem is difficult due to many factors such as intra-class variations, local deformations, articulations, viewpoint changes and missed and extraneous contour portions due to errors in shape extraction. While small local deformations have been handled in the literature by allowing some leeway in the matching of individual contour points via methods such as Chamfer distance and Hausdorff distance, handling more severe deformations and articulations has been done by applying local geometric corrections such as similarity or affine. However, determining which portions of the shape should be used for the geometric corrections is very hard, although some methods have been tried. In this paper, we address this problem by an efficient search for the group of contour segments to be clustered together for a geometric correction using dynamic programming by essentially searching for the segmentations of two shapes that lead to the best matching between them. At the same time, we allow portions of the contours to remain unmatched to handle missing and extraneous contour portions. Experiments indicate that our method outperforms other algorithms, especially when the shapes to be matched are more complex.


Shape matching Shape retrieval Contour segmentation Occlusion handling 


  1. 1.
    Adamek, T., O’Connor, N.E.: A multiscale representation method for nonrigid shapes with a single closed contour. In: IEEE Transactions on CSVT (2004)Google Scholar
  2. 2.
    Alajlan, N., Kamel, M., Freeman, G.: Geometry-based image retrieval in binary image databases. In: IEEE PAMI (2008)Google Scholar
  3. 3.
    Bai, X., Yang, X., Latecki, L., Liu, W., Tu, Z.: Learning context-sensitive shape similarity by graph transduction. In: IEEE PAMI (2010)Google Scholar
  4. 4.
    Bai, X., Rao, C., Wang, X.: Shape vocabulary: a robust and efficient shape representation for shape matching. In: IEEE Transactions on Image Processing (2014)Google Scholar
  5. 5.
    Belongie, S., Puzhicha, J., Malik, J.: Shape matching and object recognition using shape contexts. In: IEEE PAMI (2002)Google Scholar
  6. 6.
    Bhattacharjee, S.D., Mittal, A.: Part-based deformable object detection with a single sketch. In: CVIU (2015)Google Scholar
  7. 7.
    Borgefors, G.: Distance transformations in arbitrary dimensions. Comput. Vis. Graphics Image Process. 27(3), 321–345 (1984)CrossRefGoogle Scholar
  8. 8.
    Bronstein, A.M., Bronstein, M.M., Bruckstein, A.M., Kimmel, R.: Analysis of two-dimensional non-rigid shapes. Int. J. Comput. Vis. 78, 67–88 (2008)CrossRefGoogle Scholar
  9. 9.
    Brox, T., Bourdev, L., Maji, S., Malik, J.: Object segmentation by alignment of poselet activations to image contours. In: CVPR (2011)Google Scholar
  10. 10.
    Bryner, D., Klassen, E., Le, H., Srivastava, A.: 2d affine and projective shape analysis. In: IEEE PAMI (2014)Google Scholar
  11. 11.
    Cao, Y., Zhang, Z., Czogiel, I., Dryden, I., Wang, S.: 2d nonrigid partial shape matching using MCMC and contour subdivision. In: CVPR (2011)Google Scholar
  12. 12.
    Chen, L., Feris, R., Turk, M.: Efficient partial shape matching using Smith–Waterman algorithm. In: CVPRW, pp 1–6 (2008)Google Scholar
  13. 13.
    Cohignac, T., Lopez, C., Morel, J.M.: Integral and local affine invariant parameter and application to shape recognition. In: ICPR (1994)Google Scholar
  14. 14.
    Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms. MIT Press, Cambridge (2001)zbMATHGoogle Scholar
  15. 15.
    Daliri, M.R., Torre, V.: Robust symbolic representation for shape recognition and retrieval. Pattern Recognit. 41(5), 1782–1798 (2008)CrossRefzbMATHGoogle Scholar
  16. 16.
    Elad, A., Kimmel, R,: On bending invariant signatures fir surfaces. In: IEEE PAMI (2003)Google Scholar
  17. 17.
    Felzenszwalb, P.: Representation and detection of deformable shapes. In: IEEE PAMI (2005)Google Scholar
  18. 18.
    Felzenszwalb, P., Schwartz, J.: Hierarchical matching of deformable shapes. In: CVPR (2007)Google Scholar
  19. 19.
    Ferrari, V., Fevrier, L., Jurie, F., Schmid, C.: Groups of adjacent contour segments for object detection. IEEE 30, 36–51 (2008)Google Scholar
  20. 20.
    Gopalan, R., Turaga, P., Chellappa, R.: Articulation-invariant representation of non-planer shapes. In: Proceedings of the 11th European Conference on Computer Vision Conference on Computer Vision: Part III, pp. 286–299. Springer (2010)Google Scholar
  21. 21.
    Guo, G., Wang, Y., Jiang, T., Yuille, A.L., Fang, F., Gao, W.: A shape reconstructability measure of object part importance with applications to object detection and localization. In: IJCV (2014)Google Scholar
  22. 22.
    He, X., Yung, N.H.C.: Curvature scale space corner detector with adaptive threshold and dynamic region of support. In: ICPR (2004)Google Scholar
  23. 23.
    Hoffman, D.D., Richards, W.: Parts of cognition. Cognition 18, 65–96 (1984)CrossRefGoogle Scholar
  24. 24.
    Hong, B.W., Prados, E., Soatto, S., Vese, L.: Shape representation based on integral kernels: application to image matching and segmentation. In: CVPR (2006)Google Scholar
  25. 25.
    Huang, X., Paragios, N., Metaxas, D.N.: Shape registration in implicit spaces using information theory and free form deformations. In: IEEE PAMI (2006)Google Scholar
  26. 26.
    Huttenlocher, D., Klanderman, G., Rucklidge, W.: Comparing images using the hausdorff distance. In: IEEE PAMI (1993)Google Scholar
  27. 27.
    Kumar, N., Belhumeur, P.N., Biswas, A., Jacobs, D.W., Kress, W.J., Lopez, I.C., Soares, J.V.B.: Leafsnap: a computer vision system for automatic plant species identification. In: ECCV (2012)Google Scholar
  28. 28.
    Latecki, L., Lakamper, R.: Shape similarity measure based on correspondence of visual parts. In: IEEE PAMI (2000)Google Scholar
  29. 29.
    Latecki, L., Lakamper, R., Eckhardt, T.: Shape descriptors for non-rigid shapes with a single closed contour. In: CVPR (2000)Google Scholar
  30. 30.
    Latecki, L.J., Megalooikonomou, V., Wang, Q., Yu, D.: An elastic shape matching technique. Pattern Recognit. 40(11), 3069–3080 (2007)CrossRefzbMATHGoogle Scholar
  31. 31.
    Ling, H., Jacobs, D.: Shape classification using the inner-distance. IEEE PAMI 29(2), 286–299 (2007)CrossRefGoogle Scholar
  32. 32.
    Ling, H., Okada, K.: An efficient earth mover’s distance algorithm for robust histogram comparison. In: IEEE PAMI (2007)Google Scholar
  33. 33.
    Liu, H., Liu, W., Latecki, L.: Convex shape decomposition. In: CVPR (2010a)Google Scholar
  34. 34.
    Liu, M.Y., Tuzel, O., Veeraraghavan, A., Chellappa, R.: Fast directional chamfer matching. In: CVPR (2010b)Google Scholar
  35. 35.
    Lu, C., Latecki, L.J., Adluru, N., Yang, X., Ling, H.: Shape guided contour grouping with particle filters. In: ICCV (2009)Google Scholar
  36. 36.
    Ma, T., Latecki, L.: From partial shape matching through local information to robust global shape similarity for object detection. In: CVPR (2011)Google Scholar
  37. 37.
    Macrini, D., Dickinson, S.J., Fleet, D.J., Siddiqi, K.: Bone graphs: medial shape parsing and abstraction. In: CVIU (2011)Google Scholar
  38. 38.
    McNeill, G., Vijayakumar, S.: Hierarchical procrustes matching for shape retrieval. In: CVPR (2006)Google Scholar
  39. 39.
    Mokhtarian, F., Suomela, R.: Robust image corner detection through curvature scale space. In: IEEE PAMI (1998)Google Scholar
  40. 40.
    Mori, G., Belongie, S., Malik, J.: Efficient shape matching using shape contexts. In: IEEE PAMI (2005)Google Scholar
  41. 41.
    Ravishankar, S., Jain, A., Mittal, A.: Multi-stage contour based detection of deformable objects. In: ECCV (2008)Google Scholar
  42. 42.
    Russell, C., Torr, P.H.S., Kohli, P.: Associative hierarchical CRFS for object class image segmentation. In: ICCV (2009)Google Scholar
  43. 43.
    Sebastian, T., Klein, P., Kimia, B.: Recognition of shapes by editing their shock graphs. In: IEEE PAMI (2004)Google Scholar
  44. 44.
    Shotton, J., Blake, A., Cipolla, R.: Multiscale categorical object recognition using contour fragments. In: IEEE PAMI (2008)Google Scholar
  45. 45.
    Siddiqi, K., Shokoufandeh, A., Dickinson, S., Zucker, S.: Shock graphs and shape matching. Int. J. Comput. Vis. 35, 13–32 (1999)CrossRefGoogle Scholar
  46. 46.
    Super, B.J.: Retrieval from shape databases using chance probability functions and fixed correspondence. Int. J. Pattern Recognit. Artif. Intell. 20, 1117–1138 (2006)CrossRefGoogle Scholar
  47. 47.
    Temlyakov, A., Munsell, B., Waggoner, J., Wang, S.: Two perceptually motivated strategies for shape classification. In: CVPR (2010)Google Scholar
  48. 48.
    Tu, Z., Yuille, A.: Shape matching and recognition—using generative models and informative features. In: ECCV (2004)Google Scholar
  49. 49.
    Tuytelaars, T., Mikolajczyk, K.: Local invariant feature detectors: a survey. In: Foundations and Trends in Computer Graphics and Vision (2008)Google Scholar
  50. 50.
    Wang, J., Bai, X., You, X., Liu, W., Latecki, L.J.: Shape matching and classification using height functions. In: PRL (2012)Google Scholar
  51. 51.
    Wang, X., Feng, B., Bai, X., Liu, W., Latecki, L.J.: Bag of contour fragments for robust shape classification. Pattern Recognit. 47, 2116–2125 (2014)CrossRefGoogle Scholar
  52. 52.
    Xu, C., Liu, J., Tang, X.: 2d shape matching by contour flexibility. In: IEEE PAMI (2009)Google Scholar
  53. 53.
    Yang, X., Koknar-Tezel, S., Latecki, L.: Locally constrained diffusion process on locally densified distance spaces with applications to shape retrieval. In: CVPR (2009)Google Scholar
  54. 54.
    Zhang, D., Lu, G.: Review of shape representation and description techniques. Pattern Recognit. 37(1), 1–19 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Computer Science and Engineering DepartmentIndian Institute of Technology, MadrasChennaiIndia

Personalised recommendations