Advertisement

Handwritten Character Recognition of Popular South Indian Scripts

  • Umapada Pal
  • Nabin Sharma
  • Tetsushi Wakabayashi
  • Fumitaka Kimura
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4768)

Abstract

India is a multi-lingual, multi-script country. Considerably less work has been done towards handwritten character recognition of Indian languages than for other languages. In this paper we propose a quadratic classifier based scheme for the recognition of off-line handwritten characters of three popular south Indian scripts: Kannada, Telugu, and Tamil. The features used here are mainly obtained from the directional information. For feature computation, the bounding box of a character is segmented into blocks, and the directional features are computed in each block. These blocks are then down-sampled by a Gaussian filter, and the features obtained from the down-sampled blocks are fed to a modified quadratic classifier for recognition. Here, we used two sets of features. We used 64-dimensional features for high speed recognition and 400-dimensional features for high accuracy recognition. A five-fold cross validation technique was used for result computation, and we obtained 90.34%, 90.90%, and 96.73% accuracy rates from Kannada, Telugu, and Tamil characters, respectively, from 400 dimensional features.

Keywords

Character Recognition Multi Layer Perceptron Zernike Moment Chain Code Handwritten Character 
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.
    Plamondon, R., Srihari, S.N.: On-Line and Off-line Handwritten Recognition: A Comprehensive Survey. IEEE Trans on PAMI 22, 62–84 (2000)Google Scholar
  2. 2.
    Lorigo, L., Govindaraju, V.: Arabic Handwritten Word Recognition: A Survey. IEEE Trans on PAMI 28, 712–724 (2006)Google Scholar
  3. 3.
    Pal, U., Chaudhuri, B.B.: Indian Script Character Recognition: A Survey. Pattern Recognition 37, 1887–1899 (2004)CrossRefGoogle Scholar
  4. 4.
    Kunte, R.S.R., Samuel, R.D.S.: On-line Character Recognition for Handwritten Kannada Characters using Wavelet Features and Neural Classifier. IETE Journal of Research 46, 387–392 (2000)Google Scholar
  5. 5.
    Liu, C.-L., Nakashima, K., Sako, H., Fujisawa, H.: Handwritten Digit Recognition: Benchmarking of State-of-the-Art Techniques. Pattern Recognition 36, 2271–2285 (2003)zbMATHCrossRefGoogle Scholar
  6. 6.
    Hanmandlu, M., Murthy, O.V.R.: Fuzzy Model Based Recognition of Handwritten Hindi Numerals. In: Intl.Conf. on Cognition and Recognition, pp. 490–496 (2005)Google Scholar
  7. 7.
    Bajaj, R., Dey, L., Chaudhury, S.: Devnagari Nnumeral Recognition by Combining Decision of Multiple Connectionist Classifiers. Sadhana 27, 59–72 (2002)CrossRefGoogle Scholar
  8. 8.
    Kumar, S., Singh, C.: A Study of Zernike Moments and its use in Devnagari Handwritten Character Recognition. In: Intl. Conf. on Cognition and Recognition, pp. 514–520 (2005)Google Scholar
  9. 9.
    Bhattacharya, U., Parui, S.K., Shaw, B., Bhattacharya, K.: Neural Combination of ANN and HMM for Handwritten Devnagari Numeral Recognition. In: Proc. 10th IWFHR, pp. 613–618 (2006)Google Scholar
  10. 10.
    Otsu, N.: A Threshold Selection Method from Grey Level Histogram. IEEE Trans on SMC 9, 62–66 (1979)Google Scholar
  11. 11.
    Sharma, N., Pal, U., Kimura, F., Pal, S.: Recognition of Offline Handwritten Devnagari Characters using Quadratic Classifier. In: Kalra, P.K., Peleg, S. (eds.) ICVGIP 2006. LNCS, vol. 4338, pp. 805–816. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  12. 12.
    Kimura, F., Takashina, K., Tsuruoka, S., Miyake, Y.: Modified Quadratic Discriminant Function and the Application to Chinese Character Recognition. IEEE Trans. on PAMI 9, 149–153 (1987)Google Scholar
  13. 13.
    Roy, K., Pal, U., Chaushuri, B.B.: A System for Joining and Recognition of Broken Bangla Characters for Indian Postal Automation. In: Proc. of 4th Indian Conf. on Computer Vision Graphics and Image Processing, pp. 641–646 (2004)Google Scholar
  14. 14.
    Pal, U., Chaudhuri, B.B.: Automatic Recognition of Unconstrained Off-line Bangla Hand-written Characters. In: Tan, T., Shi, Y., Gao, W. (eds.) ICMI 2000. LNCS, vol. 1948, pp. 371–378. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  15. 15.
    Shanthi, N., Duraiswamy, K.: Preprocessing Algorithms for Recognition of Tamil Handwritten Characters. In: 3rd Int. CALIBER (2005)Google Scholar
  16. 16.
    Chinnuswamy, P., Krishnamoorthy, S.G.: Recognition of Hand Printed Tamil Characters. Pattern Recognition 12, 141–152 (1980)CrossRefGoogle Scholar
  17. 17.
    Hewavitharana, S., Fernand, H.C.: A Two Stage Classification Approach to Tamil Handwriting Recognition. In: Tamil Internet, California, USA (2002)Google Scholar
  18. 18.
    Bhowmick, T.K., Bhattacharya, U., Parui, S.K.: Recognition of Bangla Handwritten Characters Using an MLP Classifier Based on Stroke Features. In: Pal, N.R., et al. (eds.) ICONIP 2004. LNCS, vol. 3316, pp. 814–819. Springer, Heidelberg (2004)Google Scholar
  19. 19.
    Basu, S., et al.: Handwritten Bangla Alphabet Recognition Using an MLP Based Classifier. In: Proc. of 2nd NCCPB Dhaka (2005)Google Scholar
  20. 20.
    Rahman, A.F.R., Rahman, R., Fairhurst, M.C.: Recognition of Handwritten Bengali Characters: a Novel Multistage Approach. Pattern Recognition 35, 997–1006 (2002)zbMATHCrossRefGoogle Scholar
  21. 21.
    Negi, A., Bhagvati, C., Krishna, B.: An OCR System for Telugu. In: Proc. ICDAR, pp. 1110–1114 (2001)Google Scholar
  22. 22.
    Sukhaswami, M.B., Seetharamulu, P., Pujari, A.K.: Recognition of Telugu Characters Using Neural Networks. Int. J. Neural Syst. 6, 7–357 (1995)CrossRefGoogle Scholar
  23. 23.
    Swethalakshmi, H., Jayaram, A., Chakraborty, V.S., Sekhar, C.C.: Online Handwritten Character Recognition of Devanagari and Telugu Characters using Support Vector Machines. In: Proc. 10th IWFHR, pp. 367–372 (2006)Google Scholar
  24. 24.
    Aparna, K.G., Ramakrishnan, A.G.: A Complete Tamil Optical Character Recognition System. In: Proc. in the 5th Intl. workshop on Document Analysis and Systems, pp. 53–57 (2002)Google Scholar
  25. 25.
    Kumar, B., Vijay, Ramakrishnan, A.G.: Machine Recognition of Printed Kannada Text. In: 5th Int. Workshop on DAS, pp. 37–48 (2000)Google Scholar
  26. 26.
    Pal., U., Sharma, N., Kimura, F., Pal, S.: Offline Handwritten Kannada Character Recognition. Proc. International Conference on Signal and Image Processing 1, 174–177 (2006)Google Scholar
  27. 27.
    Pal, U.: Automatic Script Identification: A Survey. Vivek 16, 26–35 (2006)Google Scholar
  28. 28.
    Kim, H.Y., Kim, J.H.: Hierarchical Random Graph Representation of Handwritten Characters and Its Application to Hangul Recognition. Pattern Recognition 34, 187–201 (2001)zbMATHCrossRefGoogle Scholar
  29. 29.
    Roy, K., Pal, U., Kimura, F.: Bangla Handwritten Character Recognition. International Journal of Tomography & Statistics 5, 27–36 (2007)Google Scholar
  30. 30.
    Sethi, I.K., Chatterjee, B.: Machine Recognition of Constrained Hand Printed Devnagari. Pattern Recognition 9, 69–75 (1977)CrossRefGoogle Scholar
  31. 31.
    Pal, U., Roy, K., Kimura, F.: A Lexicon Driven Method for Unconstrained Bangla Handwritten Word Recognition. In: Proc. 10th IWFHR, pp. 601–606 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Umapada Pal
    • 1
  • Nabin Sharma
    • 1
  • Tetsushi Wakabayashi
    • 2
  • Fumitaka Kimura
    • 2
  1. 1.Computer Vision Pattern Recognition Unit Indian Statistical InstituteKolkataIndia
  2. 2.Graduate School of EngineeringMie UniversityKurimamachiya-choJapan

Personalised recommendations