Skip to main content

Object recognition based on critical nodes

Pattern Analysis and Applications volume 22, pages 147–163 (2019)Cite this article

Abstract

In recent decades, the need for efficient and effective image search from large databases has increased. In this paper, we present a novel shape matching framework based on structures common to similar shapes. After representing shapes as medial axis graphs, in which nodes show skeleton points and edges connect nearby points, we determine the critical nodes connecting or representing a shape’s different parts. By using the shortest path distance from each skeleton (node) to each of the critical nodes, we effectively retrieve shapes similar to a given query through a transportation-based distance function. To improve the effectiveness of the proposed approach, we employ a unified framework that takes advantage of the feature representation of the proposed algorithm and the classification capability of a supervised machine learning algorithm. A set of shape retrieval experiments including a comparison with several well-known approaches demonstrate the proposed algorithm’s efficacy and perturbation experiments show its robustness.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

USD 39.95

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

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

References

  1. Hu W, Xie N, Li L, Zeng X, Maybank S (2011) A survey on visual content-based video indexing and retrieval. IEEE Trans Systems Man Cybern Part C 41(6):797–819

    Article  Google Scholar 

  2. Amanatiadis A, Kaburlasos VG, Gasteratos A, Papadakis SE (2011) Evaluation of shape descriptors for shape-based image retrieval. IET Image Process 5(5):493–499

    Article  Google Scholar 

  3. Akimaliev M, Demirci MF (2015) Improving skeletal shape abstraction using multiple optimal solutions. Pattern Recognit 48(11):3504–3515

    Article  Google Scholar 

  4. Sebastian TB, Kimia BB (2005) Curves vs. skeletons in object recognition. Signal Process 85(2):47–263

    Article  MATH  Google Scholar 

  5. Xu Y, Wang B, Liu W, Bai X (2009) Skeleton graph matching based on critical points using path similarity. In: Zha H, Taniguchi R-I, Maybank S (eds) Computer vision ACCV 2009, vol 5996 of lecture notes in computer science. Springer, Berlin, pp 456–465

  6. Demirci MF (2013) Retrieving 2D shapes using caterpillar decomposition. Mach Vis Appl 24(2):435–445

    Article  Google Scholar 

  7. Demirci MF (2012) Graph-based shape indexing. Mach Vis Appl 23(3):541–555

    Article  Google Scholar 

  8. Vleugels J, Veltkamp R (2002) Efficient image retrieval through vantage objects. Pattern Recognit 35(1):69–80

    Article  MATH  Google Scholar 

  9. Van Leuken RH, Veltkamp RC (2011) Selecting vantage objects for similarity indexing. ACM Trans Multimed Comput Commun Appl 7(3):16:1–16:18

    Google Scholar 

  10. Boluk SA, Demirci MF (2015) Shape classification based on skeleton-branch distances. In: Proceedings of the international conference on computer vision theory and applications, vol 2. Berlin, Germany, 11–14 March 2015, pp 353–359

  11. Pele O, Werman M (2009) Fast and robust earth mover’s distances. In: Proceedings of the IEEE international conference on computer vision, pp 460–467

  12. Belongie S, Malik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24(4):509–522

    Article  Google Scholar 

  13. Ling H, Jacobs D (2007) Shape classification using the inner-distance. IEEE Trans Pattern Anal Mach Intell 29(2):286–299

    Article  Google Scholar 

  14. Guocheng A, Fengjun Z, Hong’an W, Guozhong D (2010) Shape filling rate for silhouette representation and recognition. In: Proceedings of the international conference on pattern recognition, pp 507–510

  15. Shekar B, Pilar B, Kittler J (2015) An unification of inner distance shape context and local binary pattern for shape representation and classification. In: Proceedings of the 2nd international conference on perception and machine intelligence, pp 46–55

  16. Premachandran V, Kakarala R (2013) Perceptually motivated shape context which uses shape interiors. Pattern Recognit 46(8):2092–2102

    Article  Google Scholar 

  17. Sirin Y, Demirci F (2014) Skeleton filling rate for shape recognition. In: Proceedings of the international conference on pattern recognition

  18. Sirin Y, Demirci M (2017) 2d and 3d shape retrieval using skeleton filling rate. Multimed Tools Appl 76(6):7823–7848

    Article  Google Scholar 

  19. Liu T, Geiger D (1999) Approximate tree matching and shape similarity. In: Proceedings of the IEEE international conference on computer vision, vol 1, pp 456–462

  20. Sharvit D, Chan J, Tek H, Kimia B (1998) Symmetry-based indexing of image databases. In: Proceedings of the IEEE workshop on content-based access of image and video libraries, pp 56–62

  21. Siddiqi K, Bouix S, Tannenbaum A, Zucker S (2002) Hamilton–Jacobi skeletons. Int J Comput Vis 48(3):215–231

    Article  MATH  Google Scholar 

  22. Sebastian TB, Klein PN, Kimia BB (2004) Recognition of shapes by editing their shock graphs. IEEE Trans Pattern Anal Mach Intell 26(5):550–571

    Article  Google Scholar 

  23. Yang X, Bai X, Yu D, Latecki L (2007) Shape classification based on skeleton path similarity. In: Proceedings of the international conference on the energy minimization methods in computer vision and pattern recognition, pp 375–386

  24. Yasseen Z, Verroust-Blondet A, Nasri A (2016) Shape matching by part alignment using extended chordal axis transform. Pattern Recognit 57(1):115–135

    Article  Google Scholar 

  25. Kamani MM, Farhat F, Wistar S, Wang JZ (2016) Shape matching using skeleton context for automated bow echo detection. In: IEEE international conference on Big Data (Big Data), pp 901–908

  26. Yang C, Tiebe O, Shirahama K, Grzegorzek M (2016) Object matching with hierarchical skeletons. Pattern Recognit 55:183–197

    Article  Google Scholar 

  27. Bal G, Diebold J, Chambers EW, Gasparovic E, Hu R, Leonard K, Shaker M, Wenk C (2015) Skeleton-based recognition of shapes in images via longest path matching. Springer, Cham, pp 81–99

    MATH  Google Scholar 

  28. Bai X, Liu W, Tu Z (2009) Integrating contour and skeleton for shape classification. In: Proceedings of the IEEE international conference on computer vision workshops, pp 360–367

  29. Yang C, Tiebe O, Pietsch P, Feinen C, Kelter U, Grzegorzek M (2014) Shape-based object retrieval by contour segment matching. In: Proceedings of the IEEE international conference on image processing, pp 2202–2206

  30. Bai X, Latecki LJ (2008) Path similarity skeleton graph matching. IEEE Trans Pattern Anal Mach Intell 30(7):1282–1292

    Article  Google Scholar 

  31. Shen W, Jiang Y, Gao W, Zeng D, Wang X (2016) Shape recognition by bag of skeleton-associated contour parts. Pattern Recognit Lett 83:321–329

    Article  Google Scholar 

  32. Shen W, Wang X, Yao C, Bai X (2014) Shape recognition by combining contour and skeleton into a mid-level representation. In: Pattern recognition. Springer, pp 391–400

  33. Wang X, Feng B, Bai X, Liu W, Latecki LJ (2014) Bag of contour fragments for robust shape classification. Pattern Recognit 47(6):2116–2125

    Article  Google Scholar 

  34. Wang J, Yang J, Yu K, Lv F, Huang T, Gong Y (2010) Locality-constrained linear coding for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3360–3367

  35. Bai X, Wang X, Latecki LJ, Liu W, Tu Z (2009) Active skeleton for non-rigid object detection. In: Proceedings of the IEEE international conference on computer vision, pp 575–582

  36. Li Q, Luo S, Shi Z (2009) Fuzzy aesthetic semantics description and extraction for art image retrieval. Comput Math Appl 57(6):1000–1009

    Article  MathSciNet  MATH  Google Scholar 

  37. Zou K, Chan C, Peng S, Luximon A, Chen Z, Ip W (2012) Shape-based retrieval and analysis of 3D models using fuzzy weighted symmetrical depth images. Neurocomputing 89:114–121

    Article  Google Scholar 

  38. Shanmugavadivu P, Sumathy P, Vadivel A (2016) FOSIR: fuzzy-object-shape for image retrieval applications. Neurocomputing 171:719–735

    Article  Google Scholar 

  39. Chai L, Qin Z, Zhang H, Guo J, Bhanu B (2013) MFSC: a new shape descriptor with robustness to deformations. In: IEEE international conference on multimedia and expo workshops (ICMEW), pp 1–4

  40. Dimitrov P, Phillips C, Siddiqi K (2000) Robust and efficient skeletal graphs. In: Proceedings of the IEEE conference on computer vision and pattern recognition, vol 1, pp 417–423

  41. Shaked D, Bruckstein A (1998) Pruning medial axes. Computer Vis Image Underst 69(2):156–169

    Article  Google Scholar 

  42. Ogniewicz R, Kübler O (1995) Hierarchic voronoi skeletons. Pattern Recognit 28(3):343–359

    Article  Google Scholar 

  43. Shen W, Bai X, Hu R, Wang H, Jan Latecki L (2011) Skeleton growing and pruning with bending potential ratio. Pattern Recognit 44(2):196–209

    Article  Google Scholar 

  44. Macrini D, Siddiqi K, Dickinson S (2008) From skeletons to bone graphs: medial abstraction for object recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–8

  45. Feldman J, Singh M (2006) Bayesian estimation of the shape skeleton. Proc Natl Acad Sci 103(47):18014–18019

    Article  MathSciNet  MATH  Google Scholar 

  46. Pkalska E, Duin RPW, Paclík P (2006) Prototype selection for dissimilarity-based classifiers. Pattern Recognit 39(2):189–208

    Article  MATH  Google Scholar 

  47. Bustos B, Navarro G, Chávez E (2003) Pivot selection techniques for proximity searching in metric spaces. Pattern Recognit Lett 24(14):2357–2366

    Article  MATH  Google Scholar 

  48. Brisaboa NR, Farina A, Pedreira O, Reyes N (2006) Similarity search using sparse pivots for efficient multimedia information retrieval. In: Proceedings of the IEEE international symposium on multimedia, Washington, DC, USA, pp 881–888

  49. Lowe D (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60:91–110

    Article  Google Scholar 

  50. Ke Y, Sukthankar R (2004) PCA-SIFT: a more distinctive representation for local image descriptors. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Washington, DC, USA, pp 506–513

  51. Bay H, Ess A, Tuytelaars T, Van Gool L (2008) Speeded-up robust features (surf). Comput Vis Image Underst 110(3):346–359

    Article  Google Scholar 

  52. Calonder M, Lepetit V, Strecha C, Fua P (2010) Brief: binary robust independent elementary features. In: Proceedings of the European conference on computer vision: part IV. Springer, Berlin, pp 778–792

  53. Rublee E, Rabaud V, Konolige K, Bradski G (2011) ORB: an efficient alternative to sift or surf. In: Proceedings of the international conference on computer vision, ICCV ’11. IEEE Computer Society, Washington, DC, USA, pp 2564–2571

  54. Loncomilla P, del Solar JR, Martnez L (2016) Object recognition using local invariant features for robotic applications: a survey. Pattern Recognit 60:499–514

    Article  Google Scholar 

  55. Garcia-Fidalgo E, Ortiz A (2015) Vision-based topological mapping and localization methods: a survey. Robot Auton Syst 64:1–20

    Article  Google Scholar 

  56. Blum H (1967) A transformation for extracting new descriptors of shape. In: Wathen-Dunn W (ed) Models for the perception of speech and visual form. MIT Press, Cambridge, pp 362–380

    Google Scholar 

  57. Demirci F, Shokoufandeh A, Dickinson S (2009) Skeletal shape abstraction from examples. IEEE Trans Pattern Anal Mach Intell 31(5):944–952

    Article  Google Scholar 

  58. Reinders F, Jacobson M, Post F (2000) Skeleton graph generation for feature shape description. In: de Leeuw W, van Liere R (eds) Data visualization 2000, eurographics. Springer, Vienna, pp 73–82

    Chapter  Google Scholar 

  59. Eberly D (1994) A differential geometric approach to anisotropic diffusion. In: Haar Romeny B (ed) Geometry-driven diffusion in computer vision, vol 1 of computational imaging and vision, vol 1. Springer, Dordrecht, pp 371–392

    Chapter  Google Scholar 

  60. Stricker MA, Orengo M (1995) Similarity of color images. In: Storage and retrieval for image and video databases (SPIE), pp 381–392

  61. Demirci F, Shokoufandeh A, Keselman Y, Bretzner L, Dickinson S (2006) Object recognition as many-to-many feature matching. Int J Comput Vis 69(2):203–222

    Article  MATH  Google Scholar 

  62. Huber R, Ramoser H, Mayer K, Penz H, Rubik M (2005) Classification of coins using an eigenspace approach. Pattern Recognit Lett 26(1):61–75

    Article  Google Scholar 

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

    Article  MATH  Google Scholar 

  64. Cohen SD, Guibas LJ (1999) The earth mover’s distance under transformation sets. In: Proceedings of the international conference on computer vision, Kerkyra, Greece, pp 1076–1083

  65. Shen W, Bai X, Hu R, Wang H, Latecki LJ (2011) Skeleton growing and pruning with bending potential ratio. Pattern Recognit 44(2):196–209

    Article  Google Scholar 

  66. Aslan C, Tari S (2005) An axis-based representation for recognition. In: Proceedings of the IEEE international conference on computer vision, pp 1339–1346

  67. Sun K, Super B (2005) Classification of contour shapes using class segment sets. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 727–733

  68. Geusebroek J, Burghouts G, Smeulders A (2005) The amsterdam library of object images. Int J Comput Vis 61(1):103–112

    Article  Google Scholar 

  69. Li Z, Qu W, Cao J, Qi H, Stojmenovic M (2015) ECDS: an effective shape signature using electrical charge distribution on the shape. Pattern Recognit 48(2):402–410

    Article  Google Scholar 

  70. Rosten E, Drummond T (2006) Machine learning for high-speed corner detection. In: Proceedings of the European conference on computer vision—volume part I. Springer, Berlin, pp 430–443

  71. Oliver NM, Rosario B, Pentland AP (2000) A Bayesian computer vision system for modeling human interactions. IEEE Trans Pattern Anal Mach Intell 22(8):831–843

    Article  Google Scholar 

  72. Dias P, Kassim A, Srinivasan V (1995) A neural network based corner detection method. In: Proceedings of the IEEE international conference on neural networks, pp 2116–2120

  73. Viola PA, Jones MJ (2001) Rapid object detection using a boosted cascade of simple features. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 511–518

  74. Cottrell GW, Metcalfe J (1990) EMPATH: face, emotion, and gender recognition using holons. In: Proceedings of the advances in neural information processing systems 3, NIPS-3, San Francisco, CA, USA, pp 564–571

  75. Tamura S, Kawai H, Mitsumoto H (1996) Male/female identification from \(8 \times 6\) very low resolution face images by neural network. Pattern Recognit 29(2):331–335

    Article  Google Scholar 

  76. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 1–9

  77. Aydogdu F, Demirci M (2017) Age classification using an optimized CNN architecture. In: Proceedings of the international conference on compute and data analysis, ICCDA 2017, Lakeland, FL, USA, 19–23 May 2017, pp 233–239

Download references

Acknowledgements

This work has been supported in part by the Scientific and Technological Research Council of Turkey, TÜBİTAK (Grant# 113E500).

Author information

Authors and Affiliations

  1. Department of Computer Engineering, TOBB University of Economics and Technology, Sogutozu Cad., No:43, Ankara, Turkey

    Arda Boluk & M. Fatih Demirci

  2. Department of Computer Science, Nazarbayev University, 53 Kabanbay Batyr Ave., Astana, Kazakhstan

    M. Fatih Demirci

Authors
  1. Arda Boluk
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. Fatih Demirci
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to M. Fatih Demirci.

Additional information

Publisher's Note

Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Boluk, A., Demirci, M.F. Object recognition based on critical nodes. Pattern Anal Applic 22, 147–163 (2019). https://doi.org/10.1007/s10044-018-00777-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-018-00777-w

Keywords

  • Shape retrieval
  • Shape matching
  • Medial axis graph
  • Earth mover’s distance