Method for Detection of Wheat Grain Damage with Application of Neural Networks

  • Aleksander Kubiak
  • Zbigniew Mikrut
Conference paper
Part of the Advances in Soft Computing book series (AINSC, volume 19)


In the present paper the application of backpropagation type neural networks to assessment of wheat grain quality is described. The contours of whole and broken grains have been extracted using the log-polar transform, precisely normalised and then used as input data for the neural network. The network optimisation has been carried out and then the results have been analysed in the context of response values worked-out by the output neurones. By evaluation of the obtained results it has been found that correct recognition of the grain quality is possible on the 97% level for the learning set, and 94% level for the test set. The achieved recognition level allows the utilisation of the proposed method in industrial devices dedicated to grain quality evaluation.


Hide Layer Wheat Variety Correct Recognition Cartesian Space Common Buckwheat 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Chtioui Y., Panigrahi, S., Backer L. F. (1999) Rough sets theory as a pattern classification tool for quality assessment of edible beans. Trans. of the ASAE, vol. 42(4): 11451152Google Scholar
  2. 2.
    Chtioui Y., Bertrand D., Barba D. (1998) Feature selection by genetic algorithm. Application to seed discrimination by Artificial Vision. J. Sci. Food Agric, 76, 77–86Google Scholar
  3. 3.
    Ghazanfari. A., Irudayara J., Kusalik A. (1996) Grading pistachio nuts using neural network approach, Trans. of the ASAE, vol. 39 (6): 2319–2324Google Scholar
  4. 4.
    Kubiak A., Fornai L. (1994) Interaction between geometrical features and technological quality of polish wheat grain. Polish Journal of Food and Nutrition, 7/48, 3, 160–167Google Scholar
  5. 5.
    Mikrut Z. (2001) Recognition of objects normalised in Log-polar space using Kohonen networks. Proc. of the 2“d Int. Symp. Image and signal processing and analysis, Pula, CroatiaGoogle Scholar
  6. 6.
    Ohsawa R. Tsutsumi T. H. et al. (1998) Quantitative evaluation of common buckwheat (Fagopyrum esculentum Moench) kernel shape by elliptic Fourier descriptor. Euphtica, 101,175–183Google Scholar
  7. 7.
    Sakai N., Yonekawa S., Matsuzaki A. (1996) Two dimensional image analysis of the shape of rice and its application to separating Varieties. Journal of Food Engineering, 27, 397–407CrossRefGoogle Scholar
  8. 8.
    Schwartz E. L. (1977) Spatial mapping in the primate sensory projection: analytic structure and the relevance to perception. Biological Cybernetics, 25, 181–194CrossRefGoogle Scholar
  9. 9.
    Tadeusiewicz R., Mikrut Z. (1994) Neural Networks applied to visual pattern recognition — a comparative study. Appl. Math. and Comp. Sci., vol. 4 No. 3, 397–411Google Scholar
  10. 10.
    Weiman C. F. R. (1989) Polar exponential sensor arrays unify iconic and Hough space representation. SPIE vol. 1192: Intelligent robots and computer vision VIII Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Aleksander Kubiak
    • 1
  • Zbigniew Mikrut
    • 2
  1. 1.Food Engineering DepartmentUniversity of Warmia and MazuryOlsztynPoland
  2. 2.Institute of AutomaticsUniversity of Mining and MetallurgyKrakówPoland

Personalised recommendations