Extraction of Skeletal Shape Features Using a Visual Attention Operator

  • Roman M. Palenichka
  • Rokia Missaoui
  • Marek B. Zaremba
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3138)


The goal of the shape extraction method presented in this paper was to obtain a concise, robust, and invariant description of planar object shapes for object detection and identification purposes. The solution of this problem was chosen in the form of a piecewise-linear skeleton representation of local shapes in a limited number of salient object locations. A visual attention operator, which can measure the saliency level of image fragments, selects a set of most salient object locations for concise shape description. The proposed operator, called image relevance function, is a multi-scale non-linear matched filter, which takes local maxima at centers of locations of the objects of interest. This attention operator allows a simple extraction of vertices for the skeletal shape description by local maxima analysis.


Object Detection Shape Feature Local Shape Object Intensity Salient Location 
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.
    Wheeler, M.D., Ikeuchi, K.: Sensor modeling, probabilistic hypothesis generation, and robust localization for object recognition. IEEE Trans. Pattern Analysis and Machine Intelligence 17(3), 252–265 (1995)CrossRefGoogle Scholar
  2. 2.
    Conception, V., Wechsler, H.: Detection and localization of objects in time-varying imagery using attention, representation and memory pyramids. Pattern Recognition 29(9), 1543–1557 (1996)CrossRefGoogle Scholar
  3. 3.
    Blum, N., Nagel, R.N.: Shape description using weighted symmetric axis features. Pattern Recognition 10, 167–180 (1978)zbMATHCrossRefGoogle Scholar
  4. 4.
    Chen, Y.S., Yu, Y.T.: Thinning approaches for noisy digital patterns. Pattern Recognition 29(11), 1847–1862 (1996)CrossRefGoogle Scholar
  5. 5.
    Borgefors, G.: Distance transformation in digital images. Vision, Graphics, and Image Processing 34, 344–371 (1986)CrossRefGoogle Scholar
  6. 6.
    Borgefors, G., Ramella, G., Sanniti di Baja, G., Svenson, S.: On the multi-scale representation of 2D and 3D shapes. Graphical Models and Image Processing 61, 44–62 (1999)zbMATHCrossRefGoogle Scholar
  7. 7.
    Archelli, C., Ramella, G.: Sketching a grey-tone pattern from its distance transform. Pattern Recognition 29(12), 2033–2045 (1996)CrossRefGoogle Scholar
  8. 8.
    Hastie, T., Stuetzle, W.: Principal curves. Journal of the American Statistical Association 84(406), 502–516 (1989)zbMATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Kegl, B., et al.: Learning and design of principal curves. IEEE Trans. Pattern Analysis and Machine Intelligence 22(3), 281–297 (2000)CrossRefGoogle Scholar
  10. 10.
    Singh, R., Cherkassky, V., Papanikopoulos, N.: Self-organizing maps for the skeletonization of sparse shapes. IEEE Trans. on Neural Networks 11(1), 241–248 (2000)CrossRefGoogle Scholar
  11. 11.
    Lindeberg, T.: Detecting salient blob-like image structures and their scale with a scalespace primal sketch: a method for focus of attention. Int. Journal of Computer Vision 11, 283–318 (1993)CrossRefGoogle Scholar
  12. 12.
    Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Analysis and Machine Intelligence 20(11), 1254–1259 (1998)CrossRefGoogle Scholar
  13. 13.
    Tagare, H.D., Toyama, K., Wang, J.G.: A maximum-likelihood strategy for directing attention during visual search. IEEE Trans. Pattern Analysis and Machine Intelligence 23(5), 490–500 (2001)CrossRefGoogle Scholar
  14. 14.
    Palenichka, R.M.: A visual attention operator based on morphological models of images and maximum likelihood decision. In: Caelli, T.M., Amin, A., Duin, R.P.W., Kamel, M.S., de Ridder, D. (eds.) SPR 2002 and SSPR 2002. LNCS, vol. 2396, pp. 310–319. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  15. 15.
    Koenderink, J.J., van Doorm, A.J.: Representation of local geometry in the visual system. Biological cybernetics 55, 367–375 (1987)zbMATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Zaremba, M.B., Palenichka, R.M.: Probabilistic morphological modeling of hydrographic networks from satellite imagery using self-organizing maps. Control & Cybernetics 31(2), 343–370 (2002)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Roman M. Palenichka
    • 1
  • Rokia Missaoui
    • 1
  • Marek B. Zaremba
    • 1
  1. 1.Dept. of Computer Science and EngineeringUniversité du QuébecGatineauCanada

Personalised recommendations