Advertisement

Offline handwritten Gurmukhi character recognition: k-NN vs. SVM classifier

  • Anupam GargEmail author
  • Manish Kumar Jindal
  • Amanpreet Singh
Original Research
  • 1 Downloads

Abstract

In this paper, we analyzed the impact of combination of feature extraction and classification techniques for recognition of offline handwritten segmented Gurmukhi characters. Also principal component analysis (PCA) has been used to find efficient features from peak extent based and modified division point (MDP) based features which have further been used in the classification process. For classification, k-NN and SVM whose three different kernels, namely, linear-SVM, polynomial-SVM and RBF-SVM have been considered for recognition accuracy in this paper. The experimentation has been performed on the dataset of 8960 samples of offline handwritten Gurmukhi characters written by 160 unique writers. For selecting the training and testing dataset, five different partitioning strategies and k-fold cross validation techniques have been used. A recognition accuracy of 92.3% has been achieved, using the combination of linear-SVM, polynomial-SVM and k-NN classifiers and with the partitioning strategy of 80% data as training dataset and remaining data as testing dataset.

Keywords

Handwritten character recognition Feature extraction Classification Feature selection PCA k-NN SVM 

References

  1. 1.
    Deepu V, Madhvanath S, Ramakrishnan AG (2004) Principal component analysis for online handwritten character recognition. In: 17th international conference on pattern recognition (ICPR), vol 2, pp 327–330Google Scholar
  2. 2.
    Sundaram S, Ramakrishnan AG (2008) Two dimensional principal component analysis for online tamil character recognition. In: 11th international conference frontiers in handwriting recognition (ICFHR), pp 88–94Google Scholar
  3. 3.
    Aradhya VNM, Kumar GH, Noushath S (2008) Multilingual OCR system for south Indian scripts and English documents: an approach based on Fourier transform and principal component analysis. Eng Appl Artif Intell 21:658–668CrossRefGoogle Scholar
  4. 4.
    Sharma A, Kumar R, Sharma RK (2008) Online handwritten Gurmukhi character recognition using elastic matching. Int J Congr Image Signal Process (IJCISP) 2:391–396CrossRefGoogle Scholar
  5. 5.
    Singh B, Mittal A, Ghosh D (2011) An evaluation of different feature extractors and classifiers for offline handwritten Devanagari character recognition. J Pattern Recogn Res 2:269–277Google Scholar
  6. 6.
    Kumar M, Jindal MK, Sharma RK (2011) SVM based offline handwritten Gurmukhi character recognition. In: International workshop on soft computing and knowledge discovery, vol 758, pp 51–62Google Scholar
  7. 7.
    Bhattacharya U, Shridhar M, Parui SK, Sen PK, Chaudhuri BB (2012) Offline recognition of handwritten Bangla characters: an efficient two-stage approach. Pattern Anal Appl 15(4):445–458MathSciNetCrossRefGoogle Scholar
  8. 8.
    Kumar M, Jindal MK, Sharma RK (2011) k-NN based offline handwritten Gurmukhi character recognition. In: International conference on information and image processing, Shimla, pp 1–4Google Scholar
  9. 9.
    Kumar M, Jindal MK, Sharma RK (2011) Classification of characters and grading writers in offline handwritten Gurmukhi Script. In: International conference on information and image processing, Shimla, pp 1–4Google Scholar
  10. 10.
    Kumar M, Jindal MK, Sharma RK (2012) Offline handwritten Gurmukhi character recognition: study of different features and classifiers combinations. In: Workshop on document analysis and recognition, pp 94–99Google Scholar
  11. 11.
    Basu S, Das N, Sarkar R, Kundu M, Nasipuri M, Basu DK (2009) A hierarchical approach to recognition of handwritten Bangla characters. Pattern Recogn 42(7):1467–1484CrossRefGoogle Scholar
  12. 12.
    Kumar M, Sharma RK, Jindal MK (2013) A novel feature extraction techniquefor offline handwritten Gurmukhi character recognition. IETE J Res 59(6):687–692CrossRefGoogle Scholar
  13. 13.
    Kumar M, Jindal MK, Sharma RK (2013) MDP feature extraction technique for offline handwritten Gurmukhi character recognition. Smart Comput Rev 3(6):397–404CrossRefGoogle Scholar

Copyright information

© Bharati Vidyapeeth's Institute of Computer Applications and Management 2019

Authors and Affiliations

  • Anupam Garg
    • 1
    Email author
  • Manish Kumar Jindal
    • 2
  • Amanpreet Singh
    • 3
  1. 1.Department of Computer Science and EngineeringI. K. G. Punjab Technical UniversityJalandharIndia
  2. 2.Department of Computer Science and ApplicationsPanjab University Regional CentreMuktsarIndia
  3. 3.Department of Electronics and Communication EngineeringI. K. G. Punjab Technical UniversityJalandharIndia

Personalised recommendations