Segmentation of Scanned Insect Footprints Using ART2 for Threshold Selection

  • Bok-Suk Shin
  • Eui-Young Cha
  • Young Woon Woo
  • Reinhard Klette
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4872)


In a process of insect footprint recognition, footprint segments need to be extracted from scanned insect footprints in order to find out appropriate features for classification. In this paper, we use a clustering method in a preprocessing stage for extraction of insect footprint segments. In general, sizes and strides of footprints may be different according to type and size of an insect for recognition. Therefore we propose a method for insect footprint segment extraction using an improved ART2 algorithm regardless of size and stride of footprint pattern. In the improved ART2 algorithm, an initial threshold value for clustering is determined automatically using the contour shape of the graph created by accumulating distances between all the spots within a binarized footprint pattern image. In the experimental results, applying the proposed method to two kinds of insect footprint patterns, we illustrate that clustering is accomplished correctly.


Insect footprint segmentation Clustering ART2 algorithm 


  1. 1.
    Russel, J.: A recent survey of methods for closed populations of small mammals. unpublished report, The University of Auckland, Auckland (2003)Google Scholar
  2. 2.
    Whisson, D.A., Engeman, R.M., Collins, K.: Developing relative abundance techniques (RATs) for monitoring rodent population. Wildlife Research 32, 239–244 (2005)CrossRefGoogle Scholar
  3. 3.
    Connovation Ltd.: (last visit: August 2007), see
  4. 4.
    Deng, L., Bertinshaw, D.J., Klette, R., Klette, G., Jeffries, D.: Footprint identification of weta and other insects. In: Proc. Image Vision Computing New Zealand, pp. 191–196 (2004)Google Scholar
  5. 5.
    Gray, J.: Animal Locomotion. Weidenfeld & Nicolson, London (1968)Google Scholar
  6. 6.
    Woo, Y.W.: Performance evaluation of binarizations of scanned insect footprints. In: Klette, R., Žunić, J. (eds.) IWCIA 2004. LNCS, vol. 3322, pp. 669–678. Springer, Heidelberg (2004)Google Scholar
  7. 7.
    Rosenfeld, A., De la Torre, P.: Histogram concavity analysis as an aid in threshold selection. IEEE Transactions on System Man Cybernetics 13, 231–235 (1983)Google Scholar
  8. 8.
    Sezgin, M., Sankur, B.: Survey over image thresholding techniques and quantitative performance evaluation. J. Electronic Imaging 13, 146–165 (2004)CrossRefGoogle Scholar
  9. 9.
    Abutaleb, A.S.: Automatic thresholding of gray-level pictures using two-dimensional entropy. Computer Vision Graphics Image Processing 47, 22–32 (1989)CrossRefGoogle Scholar
  10. 10.
    Hasler, N., Klette, R., Rosenhahn, B., Agnew, W.: Footprint recognition of rodents and insects. In: Proc. Image Vision Computing New Zealand, pp. 167–173 (2004)Google Scholar
  11. 11.
    Carpenter, G.A., Grossberg, S.: The ART of adaptive pattern recognition by a self-organizing neural network. Computer 21, 77–88 (1988)CrossRefGoogle Scholar
  12. 12.
    Haykin, S.: Neural Networks: A Comprehensive Foundation, MacMillan (1994) Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Bok-Suk Shin
    • 1
  • Eui-Young Cha
    • 1
  • Young Woon Woo
    • 2
  • Reinhard Klette
    • 3
  1. 1.Dept. of Computer Science, Pusan National University, BusanKorea
  2. 2.Dept. of Multimedia Engineering, Dong-Eui University, BusanKorea
  3. 3.Dept. of Computer Science, The University of Auckland, AucklandNew Zealand

Personalised recommendations