Extraction of line drawings from gray value images by non-local analysis of edge element structures

  • M. Otte
  • H. -H. Nagel
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 588)


Edge elements defined as maxima of the gradient magnitude in gradient direction of a Gaussian-smoothed image are usually thresholded to suppress edge elements due to noise. In low contrast image regions, thresholding may suppress also edge elements which are part of a significant image structure and may thus result in the fragmentation or total loss of such structures.

Based on an exhaustive categorization of edge element configurations in 5×5 pixel environments (about 34 million cases), straight and curved line structures are enhanced in edge element pictures without applying a uniform gradient magnitude thresholding. In contrast to the traditional pixel oriented gradient magnitude thresholding approach, we check for chaining of edge elements based mainly on the gradient direction. Using second moments of the change rates of gradient properties, we either reject edge element chains as noisy or accept them as a structure underlying the original image.

The approach reported here has been designed deliberately for real-time execution. Experience with this approach applied to real world images demonstrates a significant improvement compared to a uniform thresholding approach.


Edge Detection Gradient Direction Gradient Magnitude Edge Element Gradient Orientation 
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. [Abdou & Pratt 79]
    I.E. Abdou, W.K. Pratt, Qualitative design and evaluation of enhancement/thresholding edge detectors, Proceedings of the IEEE 67 (1979) 753–763.Google Scholar
  2. [Bergholm 87]
    F. Bergholm, Edge focusing, IEEE Trans. Pattern Analysis and Machine Intelligence PAMI-9 (1987) 726–741.Google Scholar
  3. [Canning et al. 88]
    J. Canning, J.J. Kim, N. Netanyahu, A. Rosenfeld, Symbolic pixel labeling for curvilinear feature detection, Pattern Recognition Letters 8 (1988) 299–310.Google Scholar
  4. [Canny 86]
    J. Canny, A computational approach to edge detection, IEEE Trans. Pattern Analysis and Machine Intelligence PAMI-8 (1986) 679–698.Google Scholar
  5. [Chen & Siy 87]
    B.D. Chen, P. Siy, Forward/backward contour tracing with feedback, IEEE Trans. Pattern Analysis and Machine Intelligence PAMI-9 (1987) 438–446.Google Scholar
  6. [Deriche et al. 88]
    R. Deriche, J.P. Cocquerez, G. Almouzny, An efficient method to build early image description, Proc. Int. Conf. on Pattern Recognition, Rome, Italy, Nov. 14–17, 1988, pp. 588–590.Google Scholar
  7. [Haddon 88]
    J. Haddon, Generalized threshold selection for edge detection, Pattern Recognition 21 (1988) 195–203.Google Scholar
  8. [Hancock & Kittler 90]
    E.R. Hancock, J. Kittler, Edge labeling using dictionary-based relaxation, IEEE Trans. Pattern Analysis and Machine Intelligence PAMI-12 (1990) 165–181.Google Scholar
  9. [Haralick & Lee 90]
    R.M Haralick, J. Lee, Context depending edge detection and evaluation, Pattern Recognition 23 (1990) 1–19.Google Scholar
  10. [Hayden et al. 87]
    C.H. Hayden, R.C. Gonzales, A. Ploysongsang, A temporal edge-based image segmentor, Pattern Recognition 20 (1987) 281–290.Google Scholar
  11. [Johnson 90]
    R.P. Johnson, Contrast based edge detection, Pattern Recognition 23 (1990) 311–318.Google Scholar
  12. [Kittler & Illingworth 85]
    J. Kittler, J. Illingworth, Relaxation labelling algorithms — a review, Image and Vision Computing 3 (1985) 206–216.Google Scholar
  13. [Koller et al. 91]
    D. Koller, N. Heinze, H.-H. Nagel, Algorithmic characterization of vehicle trajectories from image sequences by motion verbs, Proc. IEEE Conf. Computer Vision and Pattern Recognition, Lahaina, Maui, Hawaii, June 3–6, 1991, pp. 90–95.Google Scholar
  14. [Korn 88]
    A.F. Korn, Toward a Symbolic Representation of Intensity Changes in Images, IEEE Trans. Pattern Analysis and Machine Intelligence PAMI-10 (1988) 610–625.Google Scholar
  15. [Kundu & Pal 86]
    M.K. Kundu, S.K. Pal, Thresholding for Edge Detection Using Human Psychovisual Phenomena, Pattern Recognition Letters 4 (1986) 433–441.Google Scholar
  16. [McKee & Aggarwal 75]
    J.W. McKee, J.K. Aggarwal, Finding edges of the surface of 3-D curved objects by computer, Pattern Recognition 7 (1975) 25–52.Google Scholar
  17. [Otte 90]
    M. Otte, Entwicklung eines Verfahrens zur schnellen Verarbeitung von Kantenelement-Ketten, Diplomarbeit, Institut für Algorithmen und Kognitive Systeme, Fakultät für Informatik der Universität Karlsruhe (TH), Karlsruhe, Deutschland, Mai 1990.Google Scholar
  18. [Otte & Nagel 91a]
    M. Otte, H.-H. Nagel, Prädikatenlogik als Grundlage für eine videoschnelle Kantenverbesserung, Interner Bericht, Institut für Algorithmen und Kognitive Systeme, Fakultät für Informatik der Universität Karlsruhe (TH), Karlsruhe, Deutschland, August 1991.Google Scholar
  19. [Otte & Nagel 91b]
    M. Otte, H.-H. Nagel, Extraktion von Strukturen aus Kantenelementbildern durch Auswertung von Kantenelementketten, Interner Bericht, Institut für Algorithmen und Kognitive Systeme, Fakultät für Informatik der Universität Karlsruhe (TH), Karlsruhe, Deutschland, September 1991.Google Scholar
  20. [Perona & Malik 90]
    P. Perona, J. Malik, Scale-space and edge detection using anisotropic diffusion, IEEE Trans. Pattern Analysis and Machine Intelligence PAMI-12 (1990) 629–639.Google Scholar
  21. [Sakai et al. 69]
    T. Sakai, M. Nagao, S. Fujibayashi, Line extraction and pattern detection in a photograph, Pattern Recognition 1 (1969) 233–248.Google Scholar
  22. [Topa & Schalkoff 89]
    L.C. Topa, R.J. Schalkoff, Edge Detection and Thinning in Time-Varying Image Sequences Using Spatio-Temporal Templates, Pattern Recognition 22 (1989) 143–154.Google Scholar
  23. [Wang & Zhang 89]
    P.S.P. Wang, Y.Y. Zhang, A Fast and Flexible Thinning Algorithm, IEEE Transactions on Computers 38 (1989) 741–745.Google Scholar
  24. [Williams & Shah 90]
    D.J. Williams, M. Shah, Edge contours using multiple scales, Computer Vision, Graphics, and Image Processing 51 (1990) 256–274.Google Scholar
  25. [Witkin 83]
    A.P. Witkin, Scale-space filtering, International Joint Conf. Artificial Intelligence, Karlsruhe, Germany, Aug. 8–12, 1983, pp. 1019–1021.Google Scholar
  26. [Zhang & Suen 84]
    T.Y. Zhang, C.Y. Suen, A Fast Parallel Algorithm for Thinning Digital Patterns, Communications of the ACM 27 (1984) 236–239.Google Scholar
  27. [Zucker et al. 77]
    S.W. Zucker, R.A. Hummel, A. Rosenfeld, An application of relaxation labeling to line and curve enhancement, IEEE Trans. on Computers C-26 (1977) 394–403.Google Scholar
  28. [Zuniga & Haralick 88]
    O. Zuniga, R. Haralick, Gradient threshold selection using the facet model, Pattern Recognition 21 (1988) 493–503.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  • M. Otte
    • 1
  • H. -H. Nagel
    • 1
    • 2
  1. 1.Institut für Algorithmen und Kognitive SystemeFakultät für Informatik der Universität Karlsruhe (TH)Karlsruhe 1Germany
  2. 2.Fraunhofer - Institut für Informations- und Datenverarbeitung (IITB)Karlsruhe

Personalised recommendations