Experimental Comparison of Orthogonal Moments as Feature Extraction Methods for Character Recognition

  • Miguel A. Duval
  • Sandro Vega-Pons
  • Eduardo Garea
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6419)


The selection of a good feature extraction technique is very important in any classification problem. Moments, especially orthogonal moments, seem to be a powerful option in the case of digital image compression, description and recognition. Nowadays, there is a considerable amount of orthogonal moments reported in the literature, each one with some advantages and drawbacks. In this paper, we carry out an experimental comparison of several orthogonal moments for the character recognition problem. Firstly, we compare orthogonal moments with other kinds of feature extraction methods and after that, we compare the different orthogonal moments taking into account different evaluation parameters. Experiments were made by using printed and handwritten digit datasets and the well-known measures: precision, recall and accuracy were used to validate the results. This experimental study corroborates the good performance of orthogonal moments. Besides, more specific results obtained in different kinds of experimentations allow coming to conclusions that could be very useful for the community of image recognition practitioners.


Orthogonal moments Feature extraction Character recognition 


  1. 1.
    Cheriet, M., Kharma, N.: Character recognition systems: A guide for students and practitiones. Wiley Interscience, Hoboken (2007)CrossRefzbMATHGoogle Scholar
  2. 2.
    Downton, A., Impedovo, S.: Progress in Handwriting Recognition. World Scientific, Singapore (1997)CrossRefGoogle Scholar
  3. 3.
    Yap, P.: Image Analysis by Krawtchouk Moments. IEEE Transaction on Image Processing 12(11), 1367–1377 (2003)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Zhu, H., Shu, H.: Image analysis by discrete orthogonal dual Hahn moments. Pattern Recognition Letters 28, 1688–1704 (2007)CrossRefGoogle Scholar
  5. 5.
    Zhu, H., Shu, H.: Image analysis by discrete orthogonal Racah moments. Signal Processing 87, 687–708 (2007)CrossRefzbMATHGoogle Scholar
  6. 6.
    Hu, M.: Visual pattern recognition by moment invariants. IRE Trans. Info. Theory, IT 8, 179–187 (1962)zbMATHGoogle Scholar
  7. 7.
    Teague, M.R.: Image analysis via the general theory of moments. J. Opt. Soc. Am. 70, 920–930 (1980)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Khotanzad, A., Hong, Y.: Invariant image recognition by Zernike moments. IEEE Transactions on Pattern Analysis and Machine Intelligence 9(1), 489–490 (1990)CrossRefGoogle Scholar
  9. 9.
    Flusser, J.: Moments and moments invariants for pattern recognition. Wiley Interscience, Hoboken (2009)CrossRefzbMATHGoogle Scholar
  10. 10.
    Xia, T., Zhu, H.: Image description with generalized pseudo-Zernike moments. Journal of the Optical Society of America 24(1), 50–59 (2007)CrossRefGoogle Scholar
  11. 11.
    Mukundan, R.: Image analysis by Tchebichef moments. IEEE Image Analysis by Tchebichef Moments 10(9), 1357–1364 (2001)MathSciNetzbMATHGoogle Scholar
  12. 12.
    Zhou, J., Shu, H.: Image analysis by discrete orthogonal Hahn moments. In: Kamel, M.S., Campilho, A.C. (eds.) ICIAR 2005. LNCS, vol. 3656, pp. 524–531. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  13. 13.
    Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)CrossRefzbMATHGoogle Scholar
  14. 14.
    LeCun, Y., et al.: Handwritten Digit Recognition: Applications of Neural Net Chips and Automatic Learning. IEEE Communication, 41–46 (1989)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Miguel A. Duval
    • 1
  • Sandro Vega-Pons
    • 1
  • Eduardo Garea
    • 1
  1. 1.Advanced Technology Application Center (CENATAV)Cuba

Personalised recommendations