Handwritten Numeral Recognition Using Polar Histogram of Low-Level Stroke Features

  • Krishna A. ParekhEmail author
  • Mukesh M. Goswami
  • Suman K. Mitra
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1022)


The paper focuses on the handwritten numeral recognition of an Indian script, Gujarati, with the reduced dimensions of features. The proposed method employees the low-level stroke (LLS) for feature extraction and the polar histogram method for feature vector generation that enables the reduced size representation of features. The baseline experiments were performed using k-nearest neighbor (k-NN) classifier and the result was improved further using support vector machine (SVM) classifier with radial basis function (RBF) kernel. The method of the Polar histogram of LLS features was also tested on Devanagari and English handwritten numeral datasets. The accuracy of classification for Gujarati, Devanagari, and English are on par with the state-of-the-art methodologies. The experiments were also performed for mixed dataset Gujarati-English, Gujarati-Devanagari, English-Devanagari, and Gujarati-English-Devanagari. In all experiments, the feature vector size is significantly less while the accuracy is not compromised much.


Handwritten numerals Polar histogram Low-level stroke features 


  1. 1.
    Baheti, M., Kale, K., Jadhav, M.: Comparison of classifiers for Gujarati numeral recognition. Int. J. Machine Intell. 3(3) (2011)Google Scholar
  2. 2.
    Belongie, S., Malik, J., Puzicha, J.: Matching shapes. In: Eighth IEEE International Conference on Proceedings of Computer Vision, 2001. ICCV 2001 . vol. 1, pp. 454–461. IEEE (2001)Google Scholar
  3. 3.
    Belongie, S., Malik, J., Puzicha, J.: Shape context: A new descriptor for shape matching and object recognition. In: Advances in Neural Information Processing Systems, pp. 831–837 (2001)Google Scholar
  4. 4.
    Bhattacharya, U., Chaudhuri, B.B.: Handwritten numeral databases of indian scripts and multistage recognition of mixed numerals. IEEE Trans. Pattern Anal. Machine Intell. 31(3), 444–457 (2009)CrossRefGoogle Scholar
  5. 5.
    Desai, A.A.: Gujarati handwritten numeral optical character reorganization through neural network. Pattern Recogn. 43(7), 2582–2589 (2010)CrossRefGoogle Scholar
  6. 6.
    Dhandra, B., Benne, R., Hangarge, M.: Kannada, Telugu and Devanagari handwritten numeral recognition with probabilistic neural network: a novel approach. Int. J. Comput. Appl. 26(9), 83–88 (2010)Google Scholar
  7. 7.
    Goswami, M.M., Mitra, S.K.: Offline handwritten gujarati numeral recognition using low-level strokes. Int. J. Appl. Pattern Recogn. 2(4), 353–379 (2015)CrossRefGoogle Scholar
  8. 8.
    Goswami, M.M., Mitra, S.K.: Classification of printed Gujarati characters using low-level stroke features. ACM Trans. Asian Low-Resource Lang. Informat. Process. (TALLIP) 15(4), 25 (2016)Google Scholar
  9. 9.
    Kompalli, S., Nayak, S., Setlur, S., Govindaraju, V.: Challenges in OCR of Devanagari documents. In: Proceedings of Eighth International Conference on Document Analysis and Recognition, 2005, pp. 327–331. IEEE (2005)Google Scholar
  10. 10.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  11. 11.
    Maloo, M., Kale, K.: Support vector machine based gujarati numeral recognition. Int. J. Comput. Sci. Eng. 3(7), 2595–2600 (2011)Google Scholar
  12. 12.
    Nagar, R., Mitra, S.K.: Feature extraction based on stroke orientation estimation technique for handwritten numeral. In: 2015 Eighth International Conference on Advances in Pattern Recognition (ICAPR), pp. 1–6. IEEE (2015)Google Scholar
  13. 13.
    Pal, U., Sharma, N., Wakabayashi, T., Kimura, F.: Handwritten numeral recognition of six popular Indian scripts. In: Ninth International Conference on Document Analysis and Recognition, 2007, ICDAR 2007, vol. 2, pp. 749–753. IEEE (2007)Google Scholar
  14. 14.
    Sethi, I.K., Chatterjee, B.: Machine recognition of constrained hand printed Devanagari. Pattern Recogn. 9(2), 69–75 (1977)CrossRefGoogle Scholar
  15. 15.
    Singh, M.J.K., Dhir, R., Rani, R.: Performance comparison of Devanagari handwritten numerals recognition. Int. J. Comput. Appl 22 (2011)Google Scholar
  16. 16.
    Zhang, Y., Wang, P.S.P.: A parallel thinning algorithm with two-subiteration that generates one-pixel-wide skeletons. In: Proceedings of the 13th International Conference on Pattern Recognition, vol. 4, pp. 457–461. IEEE (1996)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Krishna A. Parekh
    • 1
    Email author
  • Mukesh M. Goswami
    • 2
  • Suman K. Mitra
    • 1
  1. 1.DA-IICTGandhinagarIndia
  2. 2.Dharmsinh Desai UniversityNadiadIndia

Personalised recommendations