We apologize for a recent technical issue with our email system, which temporarily affected account activations. Accounts have now been activated. Authors may proceed with paper submissions. PhDFocusTM
CFP last date
20 December 2024
Reseach Article

Offline Handwritten Recognition of Curved Gujarati Consonants using GHCIR System

by Arpit Jain
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 175 - Number 13
Year of Publication: 2020
Authors: Arpit Jain
10.5120/ijca2020920607

Arpit Jain . Offline Handwritten Recognition of Curved Gujarati Consonants using GHCIR System. International Journal of Computer Applications. 175, 13 ( Aug 2020), 11-15. DOI=10.5120/ijca2020920607

@article{ 10.5120/ijca2020920607,
author = { Arpit Jain },
title = { Offline Handwritten Recognition of Curved Gujarati Consonants using GHCIR System },
journal = { International Journal of Computer Applications },
issue_date = { Aug 2020 },
volume = { 175 },
number = { 13 },
month = { Aug },
year = { 2020 },
issn = { 0975-8887 },
pages = { 11-15 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume175/number13/31512-2020920607/ },
doi = { 10.5120/ijca2020920607 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T00:24:56.170489+05:30
%A Arpit Jain
%T Offline Handwritten Recognition of Curved Gujarati Consonants using GHCIR System
%J International Journal of Computer Applications
%@ 0975-8887
%V 175
%N 13
%P 11-15
%D 2020
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Gujarati language has a variety of characters which makes the language diversified. The language has a total thirty-four consonants and eleven vowels that have different shapes. The characters have features like vertical lines, vertical lines with curves, only curve, curve with one loop and curve with two loops that differentiate the characters from one other. In this paper, the researcher has used a set of consonants which only has curves. Total eight (8) consonants ‘ક’ (k), ‘ટ’ (Ta), ‘દ’ (D), ‘ર’ (Ra), ‘ળ’ (Al), ‘ફ’ (Fa), ‘ડ’ (Da) and ‘ઝ’ (Jha) have only curve as a feature. These consonants have been taken into consideration in this research paper. For training the GHCIR system 1200 samples of each curved consonant has been collected, while the system has been tested with 100 samples of each curved consonant. The average accuracy achieved after processing for all the curved consonant is 84.25%. Further, the researcher has done the performance analysis of the Gujarati Handwritten Consonant Identification and Recognition (GHCIR) System using the Kappa coefficient. The average Kappa Coefficient justify that the system identifies all the Gujarati handwritten curved consonants with a substantial level of agreement.

References
  1. A. A. Desai, “Gujarati Handwritten Numeral OpticalCharacter Recognition Through Neural Network”, Pattern Recognition, ISSN: 0031-3203, Vol. 43, Issue 7, pp. 2582-2589, July 2010.
  2. A. A. Jain, H. A. Arolkar and C. Davda “Recognition of Offline Gujarati Handwritten Disjoint Consonants using Pattern Matching”, International Journal of Recent Technology and Engineering (IJRTE) ISSN: 2277-3878, Vol.8 Issue-3, September 2019.
  3. A. Jain and H. Arolkar, “A Survey of Gujarati Handwritten Character Recognition Techniques”, International Journal of Research in Applied Science & Engineering Technology (IJRASET), ISSN: 2321-9653; IC value:45.98, SJ Impact Factor:6.887 volume 6, Issue IX, Sep 2018.
  4. H. Thaker and C. K. Kumbharana, “Structural Feature Extraction to recognize some of the Offline Isolated Handwritten Gujarati Characters using Decision Tree Classifier”, International Journal of Computer Applications, ISSN: 0975 – 8887, Vol. 99, Issue 15, pp. 46-50, August 2014.
  5. M. J. Baheti and K. V. Kale, “Recognition of Gujarati Numerals using Hybrid Approach and Neural Networks”, International Journal of Computer Applications, ISSN:0975 -8887, and International Conference on Recent Trends in engineering & Technology – 2013 (ICRTET'2013), pp. 12- 17, 2013.
  6. M. J. Baheti and K. V. Kale, “Gujarati Numeral Recognition: Affine Invariant Moments Approach”, in First International Conference on Recent Trends in Engineering & Technology, Mar-2012 Special Issue of International Journal of Electronics, Communication & Soft Computing Science & Engineering, ISSN: 2277-9477, pp. 140-146, 2012.
  7. R. Plamondon and S. N. Srihari, “On-line and off-line handwritten recognition: a comprehensive survey”, IEEE Transactions on PAMI, Vol. 22(1), pp. 63–84, 2000.
  8. S. M. Haley and J. S. Osberg, “Kappa coefficient calculation using multiple ratings per subject: a special communication”. Physical Therapy, 69(11), 970-974, 1989.
  9. G. Cardona and D. Jain, “The Indo-Aryan Languages”, Routledge P. 115. ISBN978- 1-135-79710-2.
  10. Indo-Aryan languages, Encyclopedia Britannica Online, Retrieved 28 March 2020. https://en.wikipedia.org/wiki/Languages_of_India (On the basis of Population of 2018)
  11. Jacob Cohen Kappa Coefficient, "A coefficient of agreement for nominal scales". Educational and Psychological Measurement. 20 (1): 37–46. Retrieved on 28 March 2020. https://en.wikipedia.org/wiki/Cohen%27s_kappa#cite_note-5
  12. The Language Gulper, An Insatiable Appetite for Ancient and Modern Tongue. http://www.languagesgulper.com/ eng/Gujarati.html - retrieved on July 07, 2020.
Index Terms

Computer Science
Information Sciences

Keywords

GHCIR System Bit Combination Pattern Kappa Coefficient Thresholding