Advertisement

Integrating vocabulary clustering with spatial relations for symbol recognition

  • K. C. SantoshEmail author
  • Bart Lamiroy
  • Laurent Wendling
Original Paper

Abstract

This paper develops a structural symbol recognition method with integrated statistical features. It applies spatial organisation descriptors to the identified shape features within a fixed visual vocabulary that compose a symbol. It builds an attributed relational graph expressing the spatial relations between those visual vocabulary elements. In order to adapt the chosen vocabulary features to multiple and possible specialised contexts, we study the pertinence of unsupervised clustering to capture significant shape variations within a vocabulary class and thus refine the discriminative power of the method. This unsupervised clustering relies on cross-validation between several different cluster indices. The resulting approach is capable of determining part of the pertinent vocabulary and significantly increases recognition results with respect to the state-of-the-art. It is experimentally validated on complex electrical wiring diagram symbols.

Keywords

Spatial relations Visual vocabulary Shape descriptor Unsupervised clustering Symbol recognition 

References

  1. 1.
    Ah-Soon, C., Tombre, K.: Architectural symbol recognition using a network of constraints. Pattern Recognit. Lett. 2, 231–248 (2001)CrossRefGoogle Scholar
  2. 2.
    Bar, M., Ullman, S.: Spatial context in recognition. Perception 25, 324–352 (1993)Google Scholar
  3. 3.
    Barrat, S., Tabbone, S.: A bayesian network for combining descriptors: application to symbol recognition. Int. J. Doc. Anal. Recognit. 13(1), 65–75 (2010)CrossRefGoogle Scholar
  4. 4.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. IEEE Trans. Pattern Anal. Mach. Intell. 24(4), 509–522 (2002)CrossRefGoogle Scholar
  5. 5.
    Biederman, I.: Perceiving real-world scenes. Science 177(43), 77–80 (1972)CrossRefGoogle Scholar
  6. 6.
    Bloch, I.: Fuzzy relative position between objects in image processing: new definition and properties based on a morphological approach. Uncertain. Fuzziness Knowl. Based Syst. 7(2), 99–133 (1999)CrossRefzbMATHMathSciNetGoogle Scholar
  7. 7.
    Bodic, P. L., Locteau, H., Adam, S., Héroux, P., Lecourtier, Y., Knippel, A.: Symbol detection using region adjacency graphs and integer linear programming. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 1320–1324 (2009)Google Scholar
  8. 8.
    Bunke, H. and Messmer, B. T.: Efficient attributed graph matching and its application to image analysis. In: Braccini, C. Floriani, L.D., Vernazza, G. (eds.) Proceedings of the International Conference on Image Analysis and Processing, vol. 974. Lecture Notes in Computer Science. Springer, Berlin, pp. 45–55 (1995)Google Scholar
  9. 9.
    Carr, D.B., Young, C.J., Aster, R.C., Zhang, X.: Cluster Analysis for CTBT Seismic Event Monitoring (a study prepared for the US Department of Energy) (1999)Google Scholar
  10. 10.
    Conte, D., Foggia, P., Sansone, C., Vento, M.: Thirty years of graph matching in pattern recognition. Int. J. Pattern Recognit. Artif. Intell. 18(3), 265–298 (2004)CrossRefGoogle Scholar
  11. 11.
    Cordella, L.P., Vento, M.: Symbol and shape recognition. In: Chhabra, A.K., Dori, D. (eds.) Graphics Recognition, Recent Advances, vol. 1941. Lecture Notes in Computer Science, pp. 167–182. Springer, Berlin (2000a)Google Scholar
  12. 12.
    Cordella, L.P., Vento, M.: Symbol recognition in documents: a collection of techniques? Int. J. Doc. Anal. Recognit. 3(2), 73–88 (2000b)CrossRefGoogle Scholar
  13. 13.
    Coustaty, M., Bertet, K., Visani, M., Ogier, J.-M.: A new adaptive structural signature for symbol recognition by using a Galois lattice as a classifier. IEEE Trans. Syst. Man. Cybern. Part B Cybern. 41(4), 1136–1148 (2011)CrossRefGoogle Scholar
  14. 14.
    Davies, D.L., Bouldin, D.W.: A cluster separation measure. IEEE Trans. Pattern Anal. Mach. Intell. PAMI–1(2), 224–227 (1979)Google Scholar
  15. 15.
    Dosch, P., Lladós, J.: Vectorial signatures for symbol discrimination. In: Lladós, J., Kwon, Y.-B. (eds.) Graphics Recognition, Recent Advances and Perspectives, vol. 3088. Lecture Notes in Computer Science, pp. 154–165. Springer, Berlin (2004)Google Scholar
  16. 16.
    Dosch, P., Tombre, K., Ah-Soon, C., Masini, G.: A complete system for the analysis of architectural drawings. Int. J. Doc. Anal. Recognit. 3(2), 102–116 (2000)CrossRefGoogle Scholar
  17. 17.
    Dunn, J.C.: Well-separated clusters and optimal fuzzy partitions. J. Cybern. 4(1), 95–104 (1974)CrossRefMathSciNetGoogle Scholar
  18. 18.
    Egenhofer, M., Herring, J.R.: Categorizing Binary Topological Relations Between Regions, Lines, and Points in Geographic Databases. Research report, University of Maine (1991)Google Scholar
  19. 19.
    Freeman, J.: The modelling of spatial relations. Comput. Graph. Image Process. 4, 156–171 (1975)CrossRefGoogle Scholar
  20. 20.
    Jain, A.K., Dubes, R.C.: Algorithms for clustering data. Prentice-Hall, Upper Saddle River (1988)zbMATHGoogle Scholar
  21. 21.
    Kankanhalli, M.S., Mehtre, B.M., Wu, R.K.: Cluster-based color matching for image retrieval. Pattern Recognit. 29(4), 701–708 (1996)CrossRefGoogle Scholar
  22. 22.
    Kara, L.B., Stahovich, T.F.: An image-based, trainable symbol recognizer for hand-drawn sketches. Comput. Graph. 29(4), 501–517 (2005)CrossRefGoogle Scholar
  23. 23.
    Kim, W.-Y., Kim, Y.-S.: A region-based shape descriptor using Zernike moments. Signal Process. Image Commun. 16(1–2), 95–102 (2000)CrossRefGoogle Scholar
  24. 24.
    Lamiroy, B., Guebbas, Y.: Robust and precise circular arc detection. In: Ogier, J.-M., Liu, W., Lladós, J. (eds.) In: 8th International Workshop in Graphics Recognition. Achievements, Challenges, and Evolution (GREC), La Rochelle, France, July 22–23, 2009. Selected Papers, vol. 6020 of Lecture Notes in Computer Science. Springer, Berlin, pp. 49–60 (2010)Google Scholar
  25. 25.
    Lee, W., Kara, L.B., Stahovich, T.F.: An efficient graph-based recognizer for hand-drawn symbols. Comput. Graph. 31(4), 554–567 (2007)CrossRefGoogle Scholar
  26. 26.
    Lladós, J., Martí, E., Villanueva, J.J.: Symbol recognition by error-tolerant subgraph matching between region adjacency graphs. IEEE Trans. Pattern Anal. Mach. Intell. 23(10), 1137–1143 (2001)CrossRefGoogle Scholar
  27. 27.
    Lladós, J., Valveny, E., Sánchez, G., Martí, E.: Symbol recognition: Current advances and perspectives. In: Blostein, D., Kwon, Y.-B. (eds.) GREC—Algorithms and Applications, vol. 2390. Lecture Notes in Computer Science, pp. 104–127. Springer, Berlin (2002)Google Scholar
  28. 28.
    Matsakis, P., Wendling, L.: A new way to represent the relative position between areal objects. IEEE Trans. Pattern Anal. Mach. Intell. 21(7), 634–643 (1999)CrossRefGoogle Scholar
  29. 29.
    Messmer, B.T., Bunke, H.: Efficient subgraph isomorphism detection: a decomposition approach. IEEE Trans. Knowl. Data Eng. 12(2), 307–323 (2000)CrossRefGoogle Scholar
  30. 30.
    Miyajima, K., Ralescu, A.: Spatial organization in 2D segmented images: representation and recognition of primitive spatial relations. Fuzzy Sets Syst. 2(65), 225–236 (1994)CrossRefGoogle Scholar
  31. 31.
    Papadias, D., Theodoridis, Y.: Spatial relations, minimum bounding rectangles, and spatial data structures. Int. J. Geogr. Inf. Sci. 11(2), 111–138 (1997)CrossRefGoogle Scholar
  32. 32.
    Pham, T.V., Smeulders, A.W.M.: Learning spatial relations in object recognition. Pattern Recognit. Lett. 27(14), 1673–1684 (2006)CrossRefGoogle Scholar
  33. 33.
    Rendek, J., Masini, G., Dosch, P., Tombre, K.: The search for genericity in graphics recognition applications: design issues of the qgar software system. In: Marinai, S., Dengel, A. (eds.) Proceedings of the International Workshop on Document Analysis Systems, vol. 3163. Lecture Notes in Computer Science. Springer, Berlin, pp. 366–377 (2004)Google Scholar
  34. 34.
    Reynolds, A.P., Richards, G., de la Iglesia, B., Rayward-Smith, V.J.: Clustering rules: a comparison of partitioning and hierarchical clustering algorithms. J. Math. Model. Algorithm. 5(4), 475–504 (2006)CrossRefzbMATHGoogle Scholar
  35. 35.
    Rohlf, F.J., Fisher, D.R.: Tests for hierarchical structure in random data sets. Syst. Biol. 17(4), 407–412 (1968)CrossRefGoogle Scholar
  36. 36.
    Rousseeuw, P.: Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20(1), 53–65 (1987)CrossRefzbMATHGoogle Scholar
  37. 37.
    Rusiñol, M. and Lladós, J.: Symbol spotting in technical drawings using vectorial signatures. In: Liu, W., Lladós, J. (eds.) Graphics Recognition. Ten Years Review and Future Perspectives, vol. 3926. Lecture Notes in Computer Science. Springer, Berlin, pp. 35–46 (2006)Google Scholar
  38. 38.
    Rusiñol, M., Borràs, A., Lladós, J.: Relational indexing of vectorial primitives for symbol spotting in line-drawing images. Pattern Recognit. Lett. 31(3), 188–201 (2010)CrossRefGoogle Scholar
  39. 39.
    Saitta, S., Raphael, B., Smith, I.F.: A bounded index for cluster validity. In: Proceedings of the International Conference on Machine Learning and Data Mining in Pattern Recognition. Springer, Berlin, pp. 174–187 (2007)Google Scholar
  40. 40.
    Salmon, J.P., Wendling, L., Tabbone, S.: Improving the recognition by integrating the combination of descriptors. Int. J. Doc. Anal. Recognit. 9(1), 3–12 (2007)CrossRefGoogle Scholar
  41. 41.
    Santosh, K.C., Lamiroy, B., Ropers, J.-P.: Inductive logic programming for symbol recognition. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 1330–1334 (2009)Google Scholar
  42. 42.
    Santosh, K.C., Wendling, L., Lamiroy, B.: Unified pairwise spatial relations: an application to graphical symbol retrieval. In: Ogier, J.-M., Liu, W., Lladós, J. (eds.) Graphics Recognition. Achievements, Challenges, and Evolution, vol. 6020. Lecture Notes in Computer Science, pp. 163–174. Springer, Berlin (2010)Google Scholar
  43. 43.
    Santosh, K.C., Lamiroy, B., Wendling, L.: DTW for Matching Radon Features: A Pattern Recognition and Retrieval Method, vol. 6915. Lecture Notes in Computer Science. Springer, Berlin, pp. 249–260 (2011a)Google Scholar
  44. 44.
    Santosh, K.C., Lamiroy, B., Wendling, L.: Symbol recognition using spatial relations. Pattern Recognit. Lett. 33(3), 331–341 (2011b)CrossRefGoogle Scholar
  45. 45.
    Santosh, K.C., Lamiroy, B., Wendling, L.: Spatio-structural symbol description with statistical feature add-on. In: Kwon, Y.-B., Ogier, J.-M. (eds.) Graphics Recognition. New Trends and Challenges, vol. 7423.Lecture Notes in Computer Science, pp. 228–237. Springer, Berlin (2013)Google Scholar
  46. 46.
    Sokal, R.R., Rohlf, F.J.: The comparison of dendrograms by objective methods. Taxon 11(2), 33–40 (1962)CrossRefGoogle Scholar
  47. 47.
    Tabbone, S., Wendling, L., Salmon, J.-P.: A new shape descriptor defined on the Radon transform. Comput. Vis. Image Understand. 102(1), 42–51 (2006)CrossRefGoogle Scholar
  48. 48.
    Terrades, O.R., Valveny, E., Tabbone, S.: On the combination of ridgelets descriptors for symbol recognition. In: Liu, W., Lladós, J., Ogier, J.-M. (eds.) Graphics Recognition. Recent Advances and New Opportunities, vol. 5046. Lecture Notes in Computer Science, pp. 40–50. Springer, Berlin (2008)Google Scholar
  49. 49.
    Terrades, O.R., Valveny, E., Tabbone, S.: Optimal classifier fusion in a non-Bayesian probabilistic framework. IEEE Trans. Pattern Anal. Mach. Intell. 31(9), 1630–1644 (2009)CrossRefGoogle Scholar
  50. 50.
    Tombre, K.: Graphics recognition—what else? In: Ogier, J.-M., Liu, W., Lladós, J. (eds.) Graphics Recognition. Achievements Challenges, and Evolution, vol. 6020. Lecture Notes in Computer Science, pp. 272–277. Springer, Berlin (2010)Google Scholar
  51. 51.
    Tombre, K. and Lamiroy, B.: Pattern recognition methods for querying and browsing technical documentation. In: Proceedings of the Iberoamerican Congress on Pattern Recognition. Springer-Verlag, Berlin, pp. 504–518 (2008)Google Scholar
  52. 52.
    Tombre, K., Ah-Soon, C., Dosch, P., Habed, A., Masini, G.: Stable, robust and off-the-shelf methods for graphics recognition. In: Proceedings of International Conference on Pattern Recognition, vol. 1, p. 406 (1998)Google Scholar
  53. 53.
    Tooley, M., Wyatt, D.: Aircraft electrical and electronic systems: principles, operation and maintenance. In: Aircraft Engineering Principles and Practice. Electrical and Electronic Systems. Butterworth-Heinemann, Oxford (2008). ISBN:978-0750686952. http://www/abebooks.com/9780750686952/Aircraft-Electrical-Electronic-Systems-Principles-0750686952/plp
  54. 54.
    Valveny, E., Martí, E.: A model for image generation and symbol recognition through the deformation of lineal shapes. Pattern Recognit. Lett. 24(15), 2857–2867 (2003)CrossRefGoogle Scholar
  55. 55.
    Wang, X., Keller, J.: Human-based spatial relationship generalization through neural/fuzzy approaches. Fuzzy Sets Syst. 101(1), 5–20 (1999)CrossRefGoogle Scholar
  56. 56.
    Wenyin, L., Zhang, W., Yan, L.: An interactive example-driven approach to graphics recognition in engineering drawings. Int. J. Doc. Anal. Recognit. 9(1), 13–29 (2007)CrossRefGoogle Scholar
  57. 57.
    Xiaogang, X., Zhengxing, S., Binbin, P., Xiangyu, J., Wenyin, L.: An online composite graphics recognition approach based on matching of spatial relation graphs. Int. J. Doc. Anal. Recognit. 7(1), 44–55 (2004) Google Scholar
  58. 58.
    Yang, S.: Symbol recognition via statistical integration of pixel-level constraint histograms: a new descriptor. IEEE Trans. Pattern Anal. Mach. Intell. 27(2), 278–281 (2005)Google Scholar
  59. 59.
    Yuen, P.C., Feng, G.-C., Tang, Y.Y.: Printed chinese character similarity measurement using ring projection and distance transform. Int. J. Pattern Recognit. Artif. Intell. 12(2), 209–221 (1998)CrossRefGoogle Scholar
  60. 60.
    Zhang, D., Lu, G.: Shape-based image retrieval using generic Fourier descriptor. Signal Process. Image Commun. 17(10), 825–848 (2002)CrossRefGoogle Scholar
  61. 61.
    Zhang, D., Lu, G.: Review of shape representation and description techniques. Pattern Recognit. 37(1), 1–19 (2004)CrossRefzbMATHGoogle Scholar
  62. 62.
    Zhang, W., Wenyin, L., Zhang, K.: Symbol recognition with kernel density matching. IEEE Trans. Pattern Anal. Mach. Intell. 28(12), 2020–2024 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • K. C. Santosh
    • 1
    Email author
  • Bart Lamiroy
    • 1
  • Laurent Wendling
    • 2
  1. 1.LORIA (UMR 7503)Université de LorraineVandoeuvre-lés-Nancy CedexFrance
  2. 2.SIP, LIPADEUniversité Paris Descartes (Paris V)Paris Cedex 06France

Personalised recommendations