Character Recognition, Orientation, and Scale Estimation Thanks to the Fourier Mellin Transform

  • Sébastien Adam
  • Jean Marc. Ogier
  • Claude Cariou
  • Rémy Mullot
  • Joël Gardes
  • Jacques Labiche
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1876)


In this paper, we consider the general problem of technical document interpretation, applied to the documents of the French Telephonic Operator, France Telecom. More precisely, we focus the content of this paper on the computation of a new set of features allowing the classification of multi-oriented and multi-scaled patterns. This set of Invariant is based on the Fourier Mellin Transform. The interests of this computation rely on the possibility to use this Fourier Mellin transform within a “filtering mode”, that permits to solve the well known difficult problem of connected character recognition. In this paper, we also present an original technique allowing to compute an estimation of the orientation of each shape to be recognized.


Character Recognition Connected Pattern Zernike Moment Scale Estimation Moment Invariant 
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.
    Boatto L. and al., An interpretation system for land register maps, IEEE Computer Magazine 25 (1992), pp 25–33.Google Scholar
  2. 2.
    S.H. Joseph, P. Pridmore, Knowledge-directed Interpretation of Line Drawing Images, IEEE Trans. on PAMI, 14(9), pp 928–940, 1992Google Scholar
  3. 3.
    J.M. Ogier, R. Mullot, J. Labiche and Y. Lecourtier, Multilevel approach and distributed consistency for technical map interpretation: application to cadastral maps, Computer Vision and Image Understanding(CVIU), 70, (1998) pp 438–451.CrossRefGoogle Scholar
  4. 4.
    P. Vaxivière, K. Tombre, CELESTIN: CAD conversion of Mechanical Drawings, IEEE Computer Magazine 25 (1992), pp 46–54.Google Scholar
  5. 5.
    K. Chhabra. Graphic Symbol Recognition: An Overview, Lecture Notes in Computer Science, vol. 1389, pp 68–79, 1998.Google Scholar
  6. 6.
    M.P. Deseilligny, H. Le Men, G. Stamon, Character String Recognition on maps, a rotationinvariant recognition method, Pattern Recognition Letters, 16, pp 1297–1310, 1995.CrossRefGoogle Scholar
  7. 7.
    D. Dori, L. Wenyin, Automated CAD Conversion with the Machine Drawing Understanding System: Concepts, Algorithms, and Performances, IEEE Trans. on SMC-Part A, 29(4), pp 411–416, 1999.Google Scholar
  8. 8.
    O.D. Trier, T. Taxt, A.K. Jain, Features Extraction Methods for Character Recognition-a Survey, Pattern Recognition, 29(4), pp 641–662, 1996.CrossRefGoogle Scholar
  9. 9.
    M.K. Hu, Visual pattern recognition by moment invariants, IRE Transactions on Information Theory 8 (1962), pp 179–187.Google Scholar
  10. 10.
    M. Teague, Image analysis via the general theory of moments, Journal of Optical Society of America 70 (1980), pp 920–930.MathSciNetCrossRefGoogle Scholar
  11. 11.
    R. Bamieh, R. De Figueiredo, A general moments invariants/attributed graph method for the three dimensional object recognition from a single image, IEEE Journal of Robotics Automation 2 (1986), pp 240–242.Google Scholar
  12. 12.
    S.O. Belkasim, M. Shridar, M. Ahmadi, Pattern recognition with moment invariants: A comparative study and new results, Pattern Recognition 24 (1991), pp 1117–1138.CrossRefGoogle Scholar
  13. 13.
    M. Dai, P. Baylou, M. Najim, A efficient algorithm for computation of shape moments from run-length codes or chain codes, Pattern Recognition 25 (1992), pp 1119–1128.CrossRefGoogle Scholar
  14. 14.
    S.C. Pei, C. N. Lin, Normalisation of rotationally symmetric shapes for pattern recognition, Pattern Recognition 25 (1992), pp 913–920.CrossRefGoogle Scholar
  15. 15.
    B.C. Lin, « New forms of shape invariants from elliptic Fourier Descriptors », Pattern Recognition 20 (1987), pp 535–545.CrossRefGoogle Scholar
  16. 16.
    T. Taxt, J. B. Olafsdottir, M. Daehlen, Recognition of handwritten symbols, Pattern Recognition 23 (1990), pp 1155–1166.CrossRefGoogle Scholar
  17. 17.
    Mori, C.Y. Suen, K. Yamamoto, Historical review of OCR Research and Development, Proceedings of the IEEE, 80(7), pp 1029–1058, 1992.CrossRefGoogle Scholar
  18. 18.
    N. Kita, Object locating based on concentric circular description, in Proc. ICPR’92, Den Hague, Vol. 1 (1992), pp 637–641.Google Scholar
  19. 19.
    S.A. Dudani, K. J. Bredding, R. M. McGhee, Aircraft identification by moment invariants, IEEE Transactions on Computers 26, (1977), pp 39–45.Google Scholar
  20. 20.
    F. Ghorbel, A complete invariant description for gray level images by the harmonic analysis approach, Pattern Recognition Letters 15 (1994), pp 1043–1051.CrossRefGoogle Scholar
  21. 21.
    G. Ravichandran, M. Trivedi, Circular-Mellin features for texture segmentation, IEEE Trans. on Image Processing 4 (1995), pp 1629–1640.CrossRefGoogle Scholar
  22. 22.
    S. Adam, J.M. Ogier, C. Cariou, R. Mullot, J. Gardes, Y. Lecourtier, “ Symbol and Character Recognition: Application to Engineering Drawings ”, submitted to the International Journal on Document Analysis and Recognition (IJDAR).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Sébastien Adam
    • 1
    • 3
  • Jean Marc. Ogier
    • 1
  • Claude Cariou
    • 2
  • Rémy Mullot
    • 1
  • Joël Gardes
    • 3
  • Jacques Labiche
    • 1
  1. 1.Laboratory PSIUniversity of RouenMont Saint AignanFrance
  2. 2.LASTIENSSAT LannionLannionFrance
  3. 3.France TélécomDVSI DES/MBLBelfortFrance

Personalised recommendations