Advertisement

Handwritten digit segmentation: a comparative study

  • F. C. Ribas
  • L. S. OliveiraEmail author
  • A. S. BrittoJr.
  • R. Sabourin
Original Paper

Abstract

In this work, algorithms for segmenting handwritten digits based on different concepts are compared by evaluating them under the same conditions of implementation. A robust experimental protocol based on a large synthetic database is used to assess each algorithm in terms of correct segmentation and computational time. Results on a real database are also presented. In addition to the overall performance of each algorithm, we show the performance for different types of connections, which provides an interesting categorization of each algorithm. Another contribution of this work concerns the complementarity of the algorithms. We have observed that each method is able to segment samples that cannot be segmented by any other method, and do so independently of their individual performance. Based on this observation, we conclude that combining different segmentation algorithms may be an appropriate strategy for improving the correct segmentation rate.

Keywords

Segmentation Algorithm Handwritten Digit Segmentation Point Versus Connection Correct Segmentation 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Britto A.S., Sabourin R., Bortolozzi F., Suen C.Y.: The recognition of handwritten numeral strings using a two-stage HMM-based method. IJDAR 5, 102–117 (2003)CrossRefGoogle Scholar
  2. 2.
    Casey R., Lecolinet E.: A survey of methods and strategies in character segmentation. IEEE Trans. PAMI 18(7), 690–706 (1996)CrossRefGoogle Scholar
  3. 3.
    Chen Y.K., Wang J.F.: Segmentation of single- or multiple-touching handwritten numeral string using background and foreground analysis. IEEE Trans. Pattern Anal. Mach. Intell. 22(11), 1304–1317 (2000)CrossRefGoogle Scholar
  4. 4.
    Cheriet, M., Huang, Y.S., Suen, C.Y.: Background region based algorithm for the segmentation of connected digits. In: Proceedings of the 11th International Conference on Pattern Recognition, pp. 619–622 (1992)Google Scholar
  5. 5.
    Choi, S., Oh, I.: A segmentation-free recognition of two touching numerals using neural networks. In: Proceedings of 5th International Conference on Document Analysis and Recognition (ICDAR), pp. 253–256, Bangalore, India (1999)Google Scholar
  6. 6.
    Elnagar A., Alhajj R.: Segmentation of connected handwritten numeral strings. Pattern Recognit. 36(3), 625–634 (2003)CrossRefGoogle Scholar
  7. 7.
    Fenrich, R.: Segmentation of automatically located handwritten words. In: Proceedings of 4th IWFHR, pp. 33–44 (1991)Google Scholar
  8. 8.
    Fenrich, R., Krishnamoorthy, S.: Segmenting diverse quality handwritten digit strings in near real-time. In: Proceedings of 5th USPS Advanced Technology Conference, pp. 523–537 (1990)Google Scholar
  9. 9.
    Fujisawa H., Nakano Y., Kurino K.: Segmentation methods for character recognition: from segmentation to document structure analysis. Proc. IEEE 80, 1079–1092 (1992)CrossRefGoogle Scholar
  10. 10.
    Kim K.K., Kim J.H., Suen C.Y.: Segmentation-based recognition of handwritten touching pairs of digits using structural features. Pattern Recognit. Lett. 23(1), 13–21 (2002)zbMATHGoogle Scholar
  11. 11.
    Lei, Y., Liu, C.S., Ding, X.Q., Fu, Q.: A recognition based system for segmentation of touching handwritten numeral strings. In: Proceedings of 9th International Workshop on Frontiers of Handwriting Recognition (IWFHR), Tokyo, Japan (2004)Google Scholar
  12. 12.
    Lethelier, E., Leroux, M., Gilloux, M.: An automatic reading system for handwritten numeral amounts on french checks. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, pp. 92–97 (1995)Google Scholar
  13. 13.
    Lu Z., Chi Z., Siu W., Shi P.: A background-thinning-based approach for separating and recognizing connected handwritten digit strings. Pattern Recognit. 32, 921–933 (1999)CrossRefGoogle Scholar
  14. 14.
    Oliveira, L.S., Britto, A.S. Jr., Sabourin, R.: A synthetic database to assess segmentation algorithms. In: Proceedings of 8th International Conference on Document Analysis and Recognition, pp. 207–211 (2005)Google Scholar
  15. 15.
    Oliveira L.S., Sabourin R., Bortolozzi F., Suen C.Y.: Automatic recognition of handwritten numerical strings: a recognition and verification strategy. IEEE Trans. Pattern Anal. Mach. Intell. 24(11), 1438–1454 (2002)CrossRefGoogle Scholar
  16. 16.
    Pal U., Belaid A., Choisy C.: Touching numeral segmentation using water reservoir concept. Pattern Recognit. Lett. 24, 261–272 (2003)CrossRefGoogle Scholar
  17. 17.
    Procter, S., Elms, A.J.: The recognition of handwritten digit strings of unknown length using hidden markov models. In: Proceedings of 14th International Conference on Pattern Recognition, pp. 1515–1517 (1998)Google Scholar
  18. 18.
    Sadri J., Suen C.Y., Bui T.D.: A genetic framework using contextual knowledge for segmentation and recognition of handwritten numeral strings. Pattern Recognit. 40, 898–919 (2007)zbMATHCrossRefGoogle Scholar
  19. 19.
    Shi Z., Govindaraju V.: Segmentation and recognition of connected handwritten numeral strings. Pattern Recognit. 30(9), 1501–1504 (1997)CrossRefGoogle Scholar
  20. 20.
    Strathy, N.W.: A method for segmentation of touching handwritten numerals. Master’s thesis, Concordia University, Montreal, Canada, Sept 1993Google Scholar
  21. 21.
    Suwa, M., Naoi, S.: Segmentation of handwritten numerals by graph representation. In: Proceedings of 9th International Workshop on Frontiers of Handwriting Recognition (IWFHR), Tokyo, Japan (2004)Google Scholar
  22. 22.
    Vellasques E., Oliveira L.S., Britto A.S. Jr, Koerich A., Sabourin R.: Filtering segmentation cuts for digit string recognition. Pattern Recognit. 41(10), 3044–3053 (2008)zbMATHCrossRefGoogle Scholar
  23. 23.
    Yu D., Yan H.: Separation of touching handwritten multi-numeral strings based on morphological structural features. Pattern Recognit. 34(3), 587–598 (2001)zbMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag 2012

Authors and Affiliations

  • F. C. Ribas
    • 1
  • L. S. Oliveira
    • 2
    Email author
  • A. S. BrittoJr.
    • 1
  • R. Sabourin
    • 3
  1. 1.Pontifical Catholic University of Parana (PUCPR)CuritibaBrazil
  2. 2.Federal University of Parana (UFPR)CuritibaBrazil
  3. 3.Ecole de Technologie SuperieureMontrealCanada

Personalised recommendations