Advertisement

National Academy Science Letters

, Volume 41, Issue 1, pp 29–33 | Cite as

Offline Handwritten Numeral Recognition using Combination of Different Feature Extraction Techniques

  • Munish Kumar
  • M. K. Jindal
  • R. K. Sharma
  • Simpel Rani Jindal
Short Communication
  • 97 Downloads

Abstract

A handwritten numeral recognition system using a combination of different feature extraction techniques has been presented in this paper. Initially, we have prepared a skeleton of the numeral, so that meaningful feature information about the numeral can be extracted. For feature extraction, a combination of four types of features, namely, centroid features, diagonal features, zoning features, and peak extent based features has been used. SVM classifier has been considered for classification purpose. For experimental results, 6000 samples of isolated handwritten numerals have been considered. The proposed system achieves maximum recognition accuracy of 96.3% using five-fold cross validation technique.

Keywords

Handwritten numeral recognition Feature extraction and selection Classification-SVM 

References

  1. 1.
    Trier ØD, Jain AK, Taxt T (1996) Feature extraction methods for character recognition-A survey. Pattern Recogn 29(4):641–662CrossRefGoogle Scholar
  2. 2.
    Cordella LP, Vento M (2000) Symbol recognition in documents: a collection of techniques? Int J Doc Anal Recogn 3(2):73–88CrossRefGoogle Scholar
  3. 3.
    Chen GY, Bui TD, Krzyzak A (2003) Contour-based handwritten numeral recognition using multiwavelets and neural networks. J Pattern Recogn Soc 36(7):1598–1604CrossRefzbMATHGoogle Scholar
  4. 4.
    Romero DJ, Seijas LM, Ruedin AM (2007) Directional continuous wavelet transform applied to handwritten numerals recognition using neural networks. J Comput Sci Technol 7(1):66–71Google Scholar
  5. 5.
    Dhandra B V, Benne R G, Hangarge M (2007) Handwritten Kannada numeral recognition based on structural features. International Conference on Computational Intelligence and Multimedia Applications, pp. 224–228Google Scholar
  6. 6.
    Rajput GG, Horakeri R, Chandrakant S (2010) Printed and handwritten kannada numeral recognition using crack codes and Fourier descriptors plate. IJCA Special Issue on Recent Trends Image Process Pattern Recognition (1):53–58Google Scholar
  7. 7.
    Asthana S, Haneef F, Bhujade RK (2011) Handwritten multi-script numeral recognition using artificial neural networks. Int J Soft Comput Eng 1(1):1–5Google Scholar
  8. 8.
    Sinha G, Rani A, Dhir R, Rani R (2012) Zone based feature extraction techniques and SVM for handwritten Gurmukhi character recognition. Int J Adv Res Comput Sci Softw Eng 2(6):106–111Google Scholar
  9. 9.
    Gohil G, Teraiya R, Goyani M (2012) Chain code and Holistic features based OCR system for printed Devanagari script using ANN and SVM. Int J Intell Appl 3(1):95–104Google Scholar
  10. 10.
    Patil SB, Sinha GR (2012) Offline mixed Devanagri numerals recognition using artificial neural network. Adv Comput Res 4(1):38–41Google Scholar
  11. 11.
    Kaur M, Kumar S (2012) A recognition system for handwritten Gurmukhi characters. Int J Eng Res Technol 1(6):1–5Google Scholar
  12. 12.
    Zhang TY, Suen CY (1984) A fast parallel algorithm for thinning digital patterns. Commun ACM 27(3):236–239CrossRefGoogle Scholar
  13. 13.
    Kumar M, Sharma RK, Jindal MK (2011) SVM based offline handwritten Gurmukhi character recognition. Proc SCAKD 758:51–62Google Scholar
  14. 14.
    Kumar M, Sharma RK, Jindal MK (2013) A novel feature extraction technique for offline handwritten gurmukhi character recognition. IETE J Res 59(6):687–692CrossRefGoogle Scholar
  15. 15.
    Williams N, Zander S, Armitage G (2006) A Preliminary performance comparison of five machine learning algorithms for practical IP traffic flow classification. ACM SIGCOMM Comput Commun Rev 36:7–15CrossRefGoogle Scholar
  16. 16.
    Roy K, Vajda S, Pal U, Chaudhuri B B (2004) A system towards Indian postal automation. In: 9th International workshop on frontiers in handwriting recognition (IWFHR), pp 580–585Google Scholar
  17. 17.
    Pal U, Chaudhuri B B, Belaid A (2005) A system for bangla handwritten numeral recognition, In: International conference on cognition and recognition, pp 497–505Google Scholar
  18. 18.
    Rajput G G, Hangarge M (2007) Recognition of isolated handwritten Kannada numerals based on image fusion method, In: International conference on PReMI, pp 153–160Google Scholar
  19. 19.
    Desai AA (2010) Gujarati handwritten numeral optical character reorganization through neural network. Pattern Recogn 43(7):2582–2589CrossRefzbMATHGoogle Scholar

Copyright information

© The National Academy of Sciences, India 2018

Authors and Affiliations

  • Munish Kumar
    • 1
  • M. K. Jindal
    • 2
  • R. K. Sharma
    • 3
  • Simpel Rani Jindal
    • 4
  1. 1.Department of Computer ApplicationsGZS Campus College of Engineering & Technology (Maharaja Ranjit Singh Punjab Technical University)BathindaIndia
  2. 2.Department of Computer Science & Applications, PanjabUniversity Regional CentreMuktsarIndia
  3. 3.Department of Computer Science & EngineeringThapar UniversityPatialaIndia
  4. 4.Computer Science & EngineeringYadavindra College of EngineeringBathindaIndia

Personalised recommendations