Contact
  • E-ISSN:

    2454-9584

    P-ISSN

    2454-8111

    Impact Factor 2020

    5.051

    Impact Factor 2021

    5.610

  • E-ISSN:

    2454-9584

    P-ISSN

    2454-8111

    Impact Factor 2020

    5.051

    Impact Factor 2021

    5.610

  • E-ISSN:

    2454-9584

    P-ISSN

    2454-8111

    Impact Factor 2020

    5.051

    Impact Factor 2021

    5.610

INTERNATIONAL JOURNAL OF INVENTIONS IN ENGINEERING & SCIENCE TECHNOLOGY

International Peer Reviewed (Refereed), Open Access Research Journal
(By Aryavart International University, India)

Paper Details

ENGLISH CHARACTER RECOGNITION SYSTEM USING HYBRID CLASSIFIER BASED ON MLP AND SVM

Bashar Ibrahim Hameed

Assistant Lecturer, Master of Information Systems, Iraqi Sunni Affairs

Humam Khalid Yaseen

Assistant Lecturer, Master of Computer Science, Iraqi Sunni Affairs

Raed Sami Sarhan

Assistant Lecturer, Master of Information Systems, Ministry of Education, Iraqi-Baghdad Education Directorate Karkh, Iraq

1 - 5 Vol. 5, Jan-Dec, 2019
Receiving Date: 2018-12-12;    Acceptance Date: 2019-01-14;    Publication Date: 2019-01-17
Download PDF

Abstract

The initial stage of recognizing individual characters is through the use of machine in analyzing handwritten documents. This research focuses on the recognition of isolated characters obtained from handwritten English documents. The focus is given to the study of preprocessing and feature extraction methods. To bring about size uniformity, the character image samples are normalized to 70X50 pixel sizes using nearest neighbor interpolation method. A normalized image is next transformed into a binary image utilizing Otsu’s threshold selection technique. This is followed by thinning or contour tracing. An important concern in character recognition is the selection of best discriminative features. This study took an overview of various statistical and structural features and recommended a unique and new view on the basis of features. The effectiveness of these features on handwritten English character recognition is experimented using MultiLayer Perceptron (MLP) and Support Vector Machine (SVM) classifiers. The proposed modified view based feature is found to be very efficient. An extensive assessment experiments outcomes carried out with different features/combination of features and classifiers is presented. From the experiments, view based features are found to give high recognition accuracy. By combining different features in an optimal way, recognition accuracy of 97% is obtained. Place an order for UK cheap replica rolex watches online is convenient and guaranteed.
You can buy best 2023 panerai fake watches UK here with low price and high quality.
Do not miss the 1:1 UK perfect breitling replica watches. Place an order online and fast shipping.

Keywords: nearest neighbor interpolation; English character recognition; view based feature; support vector machine; multilayer Perceptron

    References

  1. N. Arica and F. Yarman-Vural, An Overview of Character Recognition Focused on Off-Line Handwriting, IEEE Trans. Systems, Man, and Cybernetics Part C: Applications and Rev., vol. 31, pp. 216-233, 2001.
  2. R. Plamondon and S. N. Srihari, On-Line and Off-Line Handwriting Recognition: A Comprehensive Survey, IEEE Trans. Pattern Analysis and Machine Intelligence, vo1.22, pp.63-84, 2000.
  3. Connell, Scott D., and Anil K. Jain. 'Template-based online character recognition.' Pattern Recognition 34.1 (2001): 1-14.
  4. Von Ahn, Luis, et al. 'recaptcha: Human-based character recognition via web security measures.' Science 321.5895 (2008): 1465-1468.
  5. Trier, Øivind Due, Anil K. Jain, and Torfinn Taxt. 'Feature extraction methods for character recognition-a survey.' Pattern recognition 29.4 (1996): 641-662.
  6. H. Liu and X. Ding, Handwritten Character Recognition using Gradient Feature and Quadratic Classifier with Multiple Discrimination Schemes, Proc. Eighth Inti Conf. on Document Analysis and Recognition, pp. 19-25, 2005
  7. M. Shi, Y. Fujisawa, T. Wakabayashi, and F. Kimura, Handwritten Numeral Recognition Using Gradient and Curvature of Gray Scale Image, Pattern Recognition, vol. 35(10), pp. 2051-2059, 2002.
  8. Singh, Sukhpreet, Ashutosh Aggarwal, and Renu Dhir. 'Use of Gabor Filters for recognition of Handwritten Gurmukhi character.' International Journal of Advanced Research in Computer Science and Software Engineering 2, no. 5 (2012).
  9. Wu X-Q, Wang K-Q, Zhang D (2005) Wavelet energy feature extraction and matching for palmprint recognition. J Comput Sci Technol 20(3):411–418
  10. U. Bhattacharya and B. B. Chaudhuri, Handwritten Numeral Databases of Indian Scripts and Multistage Recognition of Mixed Numerals, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 31(3), pp. 444- 457, 2009.
  11. Rajib Lochan Das, Binod Kumar Prasad, Goutam Sanyal, 'HMM based Offline Handwritten Writer Independent English Character Recognition using Global and Local Feature Extraction', International Journal of Computer Applications (0975 – 8887), Volume 46– No.10, pp. 45-50, May 2012
  12. Velappa Ganapathy, Kok Leong Liew, 'Handwritten Character Recognition Using Multiscale Neural Network Training Technique', World Academy of Science, Engineering and Technology, pp. 32-37, 2008.
  13. T.Som, Sumit Saha, 'Handwritten Character Recognition Using Fuzzy Membership Function', International Journal of Emerging Technologies in Sciences and Engineering, Vol.5, No.2, pp. 11- 15, Dec 2011.
  14. Parvez, Mohammad Tanvir, and Sabri A. Mahmoud. 'Arabic handwriting recognition using structural and syntactic pattern attributes.' Pattern Recognition 46, no. 1 (2013): 141-154
  15. Zhang, T. Y., and Ching Y. Suen. 'A fast parallel algorithm for thinning digital patterns.' Communications of the ACM 27.3 (1984): 236-239.
Back