A Study of Representation Learning for Handwritten Numeral Recognition of Multilingual Data Set

Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 10)


Handwritten numeral recognition, a subset of handwritten character recognition is the ability to identify the numbers correctly by the machine from a given input image. Compared to the printed numeral recognition, handwritten numeral recognition is more complex due to variation in writing style and shape from person to person. The success in handwritten digit recognition can be attributed to advances in machine-learning techniques. In the field of machine learning, representation-based learning in deep learning context is gaining popularity in the recent years. Representative deep learning methods have successfully implemented in image classification, action recognition, object tracking, etc. The focus of this work is to study the use of representation learning for dimensionality reduction, in offline handwritten numeral recognition. An experimental study is carried out to compare the performance of the handwritten numerals recognition using SVM-based classifier on raw features as well as on learned features. Multilingual handwritten numeral data set of English and Devanagari numbers is used for the study. The representation learning method used in the experiment is restricted Boltzmann machine (RBM).


Handwritten recognition Representation learning SVM RBM Multilingual data set Feature extraction 


  1. 1.
    Ashwin S Ramteke, Milind E Rane: A Survey on Offline Recognition of Handwritten Devanagary Script. International Journal of Scientific and Engineering Research, May 2012.Google Scholar
  2. 2.
    Ahmad, Azad: Multi Script Handwritten Numeral Recognition using Neural Network Technique. Research Journal of Science, Engineering and Management, Vo. 1, April 2012.Google Scholar
  3. 3.
    Huang, B.Q.A: Hybrid HMM-SVM Method for Online Handwriting Symbol Recognition. IEEE- 6th International Conference on Intelligent Systems Design and Applications, Vol. 1, October 2006.Google Scholar
  4. 4.
    Deng, Li: Deep Learning: Methods and Applications. Foundations and Trends® in Signal Processing, Vol. 7, 2013.Google Scholar
  5. 5.
    Kongming Liang: Representation Learning with Smooth Auto encoder, Visual Information Processing and Learning, 2014.Google Scholar
  6. 6.
    Hinton, G. E & Salakhutdinov R.R: Reducing the Dimensionality of Data with Neural Networks. pp. 504–507, Science 2006.Google Scholar
  7. 7.
    Toru Wakahara Charles C. Tappert, Ching Y. Suen: The state of the art in on-line handwriting recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 12(8), August 1990.Google Scholar
  8. 8.
    Shrivastava, Shailendra Kumar: Support Vector Machine for Handwritten Devanagari Numeral Recognition. International Journal of Computer Applications Vol. 7, October 2010.Google Scholar
  9. 9.
    Ritu Ashok Kambli, Yogesh Kailas Ankurkar and Ameya Vinay Mane: Handwritten Digit Recognition with Improved SVM. IJIST—International Journal of Innovative Science, Engineering & Technology, Vol. 1, Issue 4, June 2014.Google Scholar
  10. 10.
    Isha Vats, Shamandeep Singh: Offline Handwritten English Numeral Recognition using Correlation Method. IJERT—International Journal of Engineering Research & Technology, Vol 3, Issue 6, June 2014.Google Scholar
  11. 11.
    S.V Rajashekararadhya & P. Vanaja Rajan: Handwritten numeral/mixed numeral recognition of south Indian scripts: The zone based feature extraction method. Journal of Theoretical and applied Information Technology, 2005.Google Scholar
  12. 12.
    Larochelle, Hugo: An Empirical Evaluation of Deep Architecture on Problems with Many Factors Variation. International Conference on Machine Learning, 2007.Google Scholar
  13. 13.
    Schmidhuber, Juergen: Deep Learning in Neural Networks: An Overview, Vol 61, 2014, pp. 85–117.Google Scholar
  14. 14.
    Chet, Tan Chun: Auto encoder Neural Networks: A performance study based on Image recognition Reconstruction and Compression. Extended Abstract for masterwork Completion Seminar, 2008.Google Scholar
  15. 15.
    Hirwani, Amrita: International Journal of Advance Research in Computer Science and Management Studies, 2014, pp. 83–88.Google Scholar
  16. 16.
    Mansi Shah, Gordhan B Jethava: A Literature Review on Handwritten Character Recognition. Indian Streams Research Journal, Vol. 3, March 2013.Google Scholar
  17. 17.
    Chang, C.C. and C.J. Lin: LIBSVM: a library for support vector machines. http://www.csie.ntu.edu.tw/cjlin/libsvm.

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Carmel College of Arts Science & Commerce for WomenNuvem, SalceteIndia

Personalised recommendations