Feature Vector Definition for a Decision Tree Based Craquelure Identification in Old Paintings

  • Joanna Gancarczyk
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7583)


In the paper a new proposal of semi-automatic method of craquelure detection in old paintings is presented. It is well known, that craquelure pattern is a unique feature and its character gives a significant information about the overall condition of the work, progress and cause of its degradation and helps in dating as well as confirming the authentication of the work. There exist methods, mostly deriving from other ridge and valley recognition problems, like geodesic or medical image feature segmentation based on watershed transform, morphological operations and region growing algorithm but they sometimes fail because of a complex nature of a craquelure pattern or large scale of an analyzed area. In this work a method is presented continuing a known semi-automatic technique based on a region growing algorithm. The novel approach is to apply a decision tree based pixel segmentation method to indicate the start points of craquelure pattern. The main difficulty in this mathod is defining an adequate set of descriptors forming a feature vector for the mining model.


craquelure identification image segmentation feature detection 


  1. 1.
    Abas, F.S.: Analysis of Craquelure Patterns for Content-Based Retrieval. PhD Thesis, University of Southampton, Southampton (2004)Google Scholar
  2. 2.
    Abas, F.S., Martinez, K.: Classification of painting cracks for content-based analysis. In: IST/SPIE’s 15th Annual Symp. Electronic Imaging, Santa Clara, California, USA (2003)Google Scholar
  3. 3.
    Abas, F.S., Martinez, K.: Craquelure analysis for content-based retrieval. In: Proc of 14th Int. Conf. on Dig. Sig. Proc. Santorini, Greece, pp. 111–114 (2002)Google Scholar
  4. 4.
    Barni, M., Bartolini, F., Cappellini, V.: Image processing for virtual restoration of artworks. IEEE Multimedia 7(2), 34–37 (2000)CrossRefGoogle Scholar
  5. 5.
    Barni, M., Pelagotti, A., Piva, A.: Image processing for the analysis and conservation of paintings: opportunities and challenges. IEEE Sig. Proc. Mag., 141 (2005)Google Scholar
  6. 6.
    Bucklow, S.L.: A sylometric analysis of Craquelure. Computers and the Humanities 31, 503–521 (1998)CrossRefGoogle Scholar
  7. 7.
    Cappelllini, V., Barni, M., Corsini, M., de Rosa, A., Piva, A.: ArtShop: an art-oriented image-processing tool for cultural heritage applications. J. Visual Comput. Animat. 14, 149–158 (2003)CrossRefGoogle Scholar
  8. 8.
    Cappellini, V., Piva, A.: Opportunities and Issues of image processing for cultural heritage applications. In: Proc EUSIPCO 2006, Florence, Italy (2006)Google Scholar
  9. 9.
    Gonzalez, R.C., Woods, R.: Digital Image Processing, 3rd edn. Prentice-Hall (2007)Google Scholar
  10. 10.
    Gupta, A., Khandelwal, V., Gupta, A., Srivastava, M.C.: Image processing methods for the restoration of digitized paintings. Thammasat Int. J. Sc. Tech. 13(3), 66–72 (2008)Google Scholar
  11. 11.
    Hanbury, A., Kammerer, P., Zolda, E.: Painting crack elimination using viscous morphological reconstruction. In: Proc ICIAP 2003, Mantova, Italy (2003)Google Scholar
  12. 12.
    Microsoft Decision Trees Algorithm Technical Reference,
  13. 13.
    Tadeusiewicz, R., Korohoda, P.: Computer Analysis and Image Processing. Progress of Telecommunication Foundation Publishing House, Krakow (1997) (in Polish: Komputerowa analiza i przetwarzanie obrazow)Google Scholar
  14. 14.
    Tadeusiewicz, R.: How Intelligent Should Be System for Image Analysis? In: Kwasnicka, H., Jain, L.C. (eds.) Innovations in Intelligent Image Analysis. SCI, vol. 339, pp. V–X. Springer, Heidelberg (2011)Google Scholar
  15. 15.
    Serra, J.: Image Analysis and Mathematical Morphology, vol. I. Ac. Press, London (1982)zbMATHGoogle Scholar
  16. 16.
    Sobczyk, J., Obara, B., Fraczek, P., Sobczyk, J.: Zastosowania analizy obrazu w nieniszczacych badaniach obiektow zabytkowych. Wybrane Przyklady, Ochrona Zabytkow 2, 69–78 (2006)Google Scholar
  17. 17.
    Stork, D.G.: Computer Vision and Computer Graphics Analysis of Paintings and Drawings: An Introduction to the Literature. In: Jiang, X., Petkov, N. (eds.) CAIP 2009. LNCS, vol. 5702, pp. 9–24. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  18. 18.
    Stout, G.L.: A trial index of laminal disruption. JAIC 17(1,3), 17–26 (1977)Google Scholar
  19. 19.
    Szczepaniak, P.S., Tadeusiewicz, R.: The Role of Artificial Intelligence, Knowledge and Wisdom in Automatic Image Understanding. Journal of Applied Computer Science 18(1), 75–85 (2010)Google Scholar
  20. 20.
    De Willigen, P.: A Mathematical Study on Craquelure and other Mechanical Damage in Paintings. Delft University Press, Delft (1999)Google Scholar
  21. 21.
    Witten, I.H., Frank, E.: Data Mining. Practical Machine Learning Tools and Techniques, 2nd edn. Morgan Kaufmann Publishers, San Francisco (2005)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Joanna Gancarczyk
    • 1
  1. 1.Department of MechanicsUniversity of Bielsko-BialaBielsko-BialaPoland

Personalised recommendations