skip to main content
short-paper

A Hybrid Feature Extraction Algorithm for Devanagari Script

Authors Info & Claims
Published:21 November 2015Publication History
Skip Abstract Section

Abstract

The efficiency of any character recognition technique is directly dependent on the accuracy of the generated feature set that could uniquely represent a character and hence correctly recognize it. This article proposes a hybrid approach combining the structural features of the character and a mathematical model of curve fitting to simulate the best features of a character. As a preprocessing step, skeletonization of the character is performed using an iterative thinning algorithm based on Raster scan of the character image. Then, a combination of structural features of the character like number of endpoints, loops, and intersection points is calculated. Further, the thinned character image is statistically zoned into partitions, and a quadratic curve-fitting model is applied on each partition forming a feature vector of the coefficients of the optimally fitted curve. This vector is combined with the spatial distribution of the foreground pixels for each zone and hence script-independent feature representation. The approach has been evaluated experimentally on Devanagari scripts. The algorithm achieves an average recognition accuracy of 93.4%.

References

  1. R. Bajaj, L. Dey, and S. Chaudhury. 2002. Devnagari numeral recognition by combining decision of multiple connectionist classifiers. Sadhana 27, 1 (2002), 59--72.Google ScholarGoogle ScholarCross RefCross Ref
  2. U. Bhattacharya and B. B. Chaudhuri. 2009. Handwritten numeral databases of Indian scripts and multistage recognition of mixed numerals. IEEE Trans. Pattern Anal. Mach. Intell. 31, 3 (2009), 444--457. Google ScholarGoogle ScholarDigital LibraryDigital Library
  3. M. Blumenstein, B. Verma, and H. Basli. 2003. A novel feature extraction technique for the recognition of segmented handwritten characters. In Proceedings of the 7th International Conference on Document Analysis and Recognition (ICDAR’03). 137--141. Google ScholarGoogle ScholarDigital LibraryDigital Library
  4. K. Haghighat, A. T. Mowlaei, and A. Faez. 2002. Feature extraction with wavelet transform for recognition of isolated handwritten Farsi/Arabic characters and numerals. In Proceedings of the 14th International Conference on Digital Signal Processing, Vol. 2. 923--926.Google ScholarGoogle Scholar
  5. D. Hearn and P. Baker. 1997. Computer Graphics: C Version. Prentice Hall International. Google ScholarGoogle ScholarDigital LibraryDigital Library
  6. D. Hush and C. Scovel. 2001. On the VC dimension of bounded margin classifiers. Mach. Learn. 45, 1 (Oct. 2001), 33--44. Google ScholarGoogle ScholarDigital LibraryDigital Library
  7. F. Kimura, N. Sharma, and U. Pal. 2006. Recognition of off-line handwritten Devnagari characters using quadratic classifier. In Comp. Vision, Graphics & Image Proc. Springer, Berlin. 805--816. Google ScholarGoogle ScholarDigital LibraryDigital Library
  8. V. H. Mankar and V. J. Dongre. 2012. Development of comprehensive Devanagari numeral and character database for offline handwritten character recognition. J. Appl. Comput. Intell. Soft Comput. (ACISC) 2012. Article ID 871834. 1--5. Google ScholarGoogle ScholarDigital LibraryDigital Library
  9. N. Nain and D. Khanduja. 2013. Segmentation and recognition techniques for handwritten Devanagari script. In Proceedings of the MUSCLE International Workshop on Computational Intelligence for Multimedia Understanding. 105--111.Google ScholarGoogle Scholar
  10. F. Perez-Cruz, A. Navia-Vazquez, A. R. Figueiras-Vidal, and A. Artes-Rodriguez. 2003. Empirical risk minimization for support vector classifiers. Trans. Neur. Netw. 14, 2 (March 2003), 296--303. Google ScholarGoogle ScholarDigital LibraryDigital Library
  11. E. Himavathi Pradeep and J. Srinivasan. 2011. Neural network based handwritten character recognition system without feature extraction. In Proceedings of the International Conference on Computer, Communication and Electrical Technology (ICCCET’11). 40--44.Google ScholarGoogle Scholar
  12. S. V. Rajashekararadhya and P. V. Ranjan. 2009. Zone based feature extraction algorithm for handwritten numeral recognition of Kannada script. In Proceedings of the IEEE International Advance Computing Conference (IACC’09). 525--528.Google ScholarGoogle Scholar
  13. O. V. Ramana, M. V. K. Hanmandlu, and M. Murthy. 2007. Fuzzy model based recognition of handwritten hindi characters. In Proceedings of the 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications. 454--461. Google ScholarGoogle ScholarDigital LibraryDigital Library
  14. B. Shaw U. Bhattacharya, S. K. Parui, and K. Bhattacharya. 2006. Neural combination of ANN and HMM for handwritten Devanagari numeral recognition. In Proceedings of the 10th IWFHR. 613--618.Google ScholarGoogle Scholar
  15. T. W. Umapada Pal, S. Ch, and F. Kimura. 2008. Accuracy improvement of Devnagari character recognition combining SVM and MQDF. In Proceedings of the 11th International Conference Frontiers Handwritten Recognition SVM and MQDF. 367--372.Google ScholarGoogle Scholar

Index Terms

  1. A Hybrid Feature Extraction Algorithm for Devanagari Script

    Recommendations

    Comments

    Login options

    Check if you have access through your login credentials or your institution to get full access on this article.

    Sign in

    Full Access

    • Published in

      cover image ACM Transactions on Asian and Low-Resource Language Information Processing
      ACM Transactions on Asian and Low-Resource Language Information Processing  Volume 15, Issue 1
      January 2016
      89 pages
      ISSN:2375-4699
      EISSN:2375-4702
      DOI:10.1145/2847552
      Issue’s Table of Contents

      Copyright © 2015 ACM

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      • Published: 21 November 2015
      • Revised: 1 December 2014
      • Accepted: 1 December 2014
      • Received: 1 March 2014
      Published in tallip Volume 15, Issue 1

      Permissions

      Request permissions about this article.

      Request Permissions

      Check for updates

      Qualifiers

      • short-paper
      • Research
      • Refereed

    PDF Format

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader
    About Cookies On This Site

    We use cookies to ensure that we give you the best experience on our website.

    Learn more

    Got it!