Hybrid Approach of Handwritten Malayalam Character Recognition

  • Authors

    • Ajay James Government Engineering College, Thrissur
    • Sonu Varghese K Government Engineering College, Thrissur
    • Chandran Saravanan NIT, Durgapur
    2018-11-11
    https://doi.org/10.14419/ijet.v7i4.11944
  • Chain code, Feature extraction, Handwritten Character Recognition, Malayalam, Water reservoir technique.

  • Abstract

    Handwritten character recognition of South Indian scripts especially Malayalam is an on-going area of research. Limited works are proposed in this field due to the significant character set with highly complex and similar characters. Here hybrid technique of feature extraction based on geometrical and structural properties of characters is proposed. This method consists of two stages, in the first stage characters are
    classified into a group based on geometrical features such as the number of ending, bifurcation and loop. And in the second stage characters are recognized based on specific characteristics defined for each group. The proposed method exhibits recognition rate of 96.5% and accuracy of 93.86% on an average.

  • References

    1. [1] Lajish, V. L. â€Handwritten character recognition using perceptual fuzzy-zoning and class modular neural networks.†2007 Innovations in Information Technologies (IIT). 2007.

      [2] Raju, G. â€Wavelet transform and projection profiles in handwritten character recognition-A performance analysis.†Advanced Computing and Communications, 2008. ADCOM 2008. 16th International Conference on. IEEE, 2008.


      [3] Akram, M. Usman, et al. â€Geometric feature points based optical character recognition.†Industrial Electronics and Applications (ISIEA), 2013 IEEE Symposium on. IEEE, 2013.

      [4] Dhandra, B. V., R. G. Benne, and Mallikarjun Hangarge. â€Handwritten Kannada Numeral recognition based on structural features.†Conference on Computational Intelligence and Multimedia Applications,
      2007. International Conference on. Vol. 2. IEEE, 2007


      [5] Pal, Umapada, and Partha Pratim Roy. â€Multioriented and curved text lines extraction from Indian documents.†IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics) 34.4 (2004):
      1676-1684.


      [6] John, Jomy, K. V. Pramod, and Kannan Balakrishnan. â€Offline handwritten Malayalam Character Recognition based on chain code histogram.†Emerging Trends in Electrical and Computer Technology
      (ICETECT), 2011 International Conference on. IEEE, 2011


      [7] Moni, Bindu S., and G. Raju. â€Modified quadratic classifier for handwritten Malayalam character recognition using run length count.†Emerging Trends in Electrical and Computer Technology (ICETECT),
      2011 International Conference on. IEEE, 2011.


      [8] Rahiman, M. Abdul, et al. â€Isolated handwritten Malayalam character recognition using HLH intensity patterns.†Machine Learning and Computing (ICMLC), 2010 Second International Conference on. IEEE,
      2010.


      [9] Rahiman, M. Abdul, and M. S. Rajasree. â€An HCR System for Combinational Malayalam Handwritten Characters based on HLH Patterns.†International Journal of Computer Applications,(IJCA), USA 8.11
      (2010): 19-23.


      [10] Gayathri, P., and Sonal Ayyappan. â€Off-line handwritten character recognition using Hidden Markov Model.†Advances in Computing, Communications and Informatics (ICACCI, 2014 International Conference on. IEEE, 2014


      [11] Obaidullah, Sk Md, Anamika Mondal, and Kaushik Roy. â€Structural feature based approach for script identification from printed Indian document.†Signal Processing and Integrated Networks (SPIN), 2014 International Conference on. IEEE, 2014.


      [12] Raju, G. â€Recognition of unconstrained handwritten Malayalam characters using zero-crossing of wavelet coefficients.†2006 International Conference on Advanced Computing and Communications. IEEE, 2006.


      [13] Gatos, Basilis, Georgios Louloudis, and Nikolaos Stamatopoulos. â€Segmentation of historical handwritten documents into text zones and text lines.†Frontiers in Handwriting Recognition (ICFHR), 2014 14th International Conference on. IEEE, 2014


      [14] Fern´andez-Mota, David, Josep Llad´os, and Alicia Forn´es. â€A graphbased approach for segmenting touching lines in historical handwritten documents.†International Journal on Document Analysis and Recognition (IJDAR) 17.3 (2014): 293-312.


      [15] Bhattacharya, Ujjwal, S. K. Ghosh, and S. Parui. â€A two stage recognition scheme for handwritten Tamil characters.†Ninth International Conference on Document Analysis and Recognition (ICDAR 2007).
      Vol. 1. IEEE, 2007


      [16] Gaikwad, Ms VA, and Dr DS Bormane. â€An Overview of Character Recognition Focused On Offline Handwriting.†International Journal Of Computer Science And Applications 1.3 (2008): 0974-1003


      [17] Tokas, Rajbala, and Aruna Bhadu. â€A comparative analysis of feature extraction techniques for handwritten character recognition.†International Journal of Advanced Technology and Engineering Research 2.4 (2012): 215-219


      [18] Chacko, Anitha Mary MO, and P. M. Dhanya. â€A Comparative Study of Different Feature Extraction Techniques for Offline Malayalam Character Recognition.†Computational Intelligence in Data Mining-
      Volume 2. Springer India, 2015. 9-18.


      [19] T. R. Vijaya Lakshmi, P. Narahari Sastry, T. V. Rajinikanth, â€Hybrid Approach for Telugu Handwritten Character Recognition Using k-NN and SVM Classifiersâ€, International Review on Computers and
      Software (IRECOS), Vol 10, No 9 (2015)


      [20] Jaspreet Kaur, B. S. Dhaliwal, S. S. Gill,â€Offline Handwritten Gurmukhi Character Recognition using Particle Swarm Optimized Neural Networkâ€, International Journal of Computer Applications (0975 –
      8887) International Conference on Advances in Emerging Technology (ICAET 2016)


      [21] T. R. Vijaya LakshmiEmail authorPanyam Narahari SastryT. V. Rajinikanth,†Feature Optimization to Recognize Telugu Handwritten Characters by Implementing DE and PSO Techniquesâ€,Proceedings of
      the 5th International Conference on Frontiers in Intelligent Computing: Theory and Applications pp 397-405, 03 March 2017)


      [22] Youssef Boulid, Abdelghani Souhar, Mohamed Youssfi Elkettani,†Handwritten Character Recognition Based on the Specificity and the Singularity of the Arabic Languageâ€,International Journal of Interactive Multimedia and Artificial Intelligence · June 2017


      [23] Abhisek SethyEmail authorPrashanta Kumar PatraDeepak Ranjan Nayak,â€Off-line Odia Handwritten Character Recognition: A Hybrid Approachâ€,Computational Signal Processing and Analysis, pp 247-
      257, 03 April 2018

  • Downloads

  • How to Cite

    James, A., Varghese K, S., & Saravanan, C. (2018). Hybrid Approach of Handwritten Malayalam Character Recognition. International Journal of Engineering & Technology, 7(4), 4624-4628. https://doi.org/10.14419/ijet.v7i4.11944

    Received date: 2018-04-23

    Accepted date: 2018-07-24

    Published date: 2018-11-11