Stroke Boundary Analysis for Identification of Drawing Tools

  • Paul Kammerer
  • Georg Langs
  • Robert Sablatnig
  • Ernestine Zolda
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2905)


An algorithm for the automatic identification of drawing tools based on the appearance of the stroke boundary is presented. The purpose of this stroke analysis is the determination of drawing tools in underdrawings – the basic concept of an artist – in ancient panel paintings. This information allows significant support for a systematic stylistic approach in the analysis of paintings. Up to now the identification of drawing tools is performed by an expert visually. Our tool will support the expert to investigate larger numbers of underdrawings, provides objective and reproducible information and simplifies comparison of different underdrawings. Stroke analysis in paintings is related to the extraction and recognition of handwritings, therefore similar techniques to stroke analysis are used. Following the segmentation, the approximation of the stroke boundary is done by active contours with different parameters. Deviations between a rigid and elastic “snake” are used as descriptive features for differentiation between drawing tools. Results of the algorithm are presented for sets of three different types of strokes.


Active Contour Test Panel Segmentation Step Polygonal Boundary Drawing Tool 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Kammerer, P., Langs, G., Sablatnig, R., Zolda, E.: Stroke segmentation in infrared reflectograms. In: Bigun, J., Gustavsson, T. (eds.) SCIA 2003. LNCS, vol. 2749, pp. 1138–1145. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  2. 2.
    Van Asperen de Boer, J.R.J.: Infrared Reflectography. - A Contribution to the Examination of Earlier European Paintings. PhD thesis, Univ. Amsterdam (1970)Google Scholar
  3. 3.
    Bomford, D. (ed.): Art in the Making, Underdrawings in Renaissance Paintings. National Gallery, London (2002)Google Scholar
  4. 4.
    Plamondon, R., Srihari, S.N.: On-line and off-line handwriting recognition: A comprehensive survey. Trans. on Pattern Analysis and Machine Intelligence 22(1), 63–84 (2000)CrossRefGoogle Scholar
  5. 5.
    Doermann, D.S., Rosenfeld, A.: Recovery of temporal information from static images of handwriting. International Journal of Computer Vision 52(1-2), 143–164 (1994)Google Scholar
  6. 6.
    Xu, C., Prince, J.L.: Snakes, shapes and gradient vector flow. IEEE Transactions on image Processing 7(3), 359–369 (1998)zbMATHMathSciNetCrossRefGoogle Scholar
  7. 7.
    Langs, G., Bischof, H., Peloschek, P.L.: Automatic quantification of destructive changes caused by rheumatoid arthritis. Technical Report 79, Vienna University of Technology, Pattern Recognition and Image Processing Group (2003)Google Scholar
  8. 8.
    L’Homer, E.: Extraction of strokes in handwritten characters. Pattern Recognition 33(7), 1147–1160 (1999)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Paul Kammerer
    • 1
  • Georg Langs
    • 1
  • Robert Sablatnig
    • 1
  • Ernestine Zolda
    • 1
  1. 1.PRIPVienna University of TechnologyViennaAUSTRIA

Personalised recommendations