Novel SVD Based Character Recognition Approach for Malayalam Language Script

Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 235)


The research on character recognition for Malayalam script dates back to 1990’s. Compared to other Indian languages the research and developments on OCR reported for Malayalam script is very less. The character level and word level accuracy of the existing OCR tools for Indian languages can be improved by implementing robust character recognition and post-processing algorithms. In this paper, we are proposing a character recognition procedure based on Singular Value Decomposition (SVD) and k- Nearest Neighbor classifier (k-NN). The proposed character recognition scheme tested with the dataset created from Malayalam literature books and it could classify 94% of character images accurately.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Manjusha, K., Sachin Kumar, S., Rajendran, J., Soman, K.P.: Hindi Character Segmentation in Document Images using Level set Methods and Non-linear Diffusion. International Journal of Computer Applications (0975 - 8887) 44(16) (2012)Google Scholar
  2. 2.
    Chaudhuri, B.B.: On OCR of a Printed Indian Script. In: Advances in Pattern Recognition Digital Document Processing. Springer, London (2007)CrossRefGoogle Scholar
  3. 3.
    Kalman, D.: A Singularly Valuable Decomposition: The SVD of a Matrix. The American University, Washington (2002)Google Scholar
  4. 4.
    Digital Library of India, (cited December 10, 2012)
  5. 5.
    Malayalam Language, (cited March 7, 2013)
  6. 6.
    Cherian, M., Radhika, G., Shajeesh, K.U., Soman, K.P., Sabarimalai Manikandan, M.: A Levelset Based Binarization and Segmentation for Scanned Malayalam Document Image Analysis. In: IEEE International Conference on Computational Intelligence and Computing Research (2011)Google Scholar
  7. 7.
    Meshesha, M.: Recognition and Retrieval from Document Image Collections. Ph. D. Thesis, IIIT Hyderabad, India (2008)Google Scholar
  8. 8.
    Neeba, N.V., Namboodiri, A., Jawahar, C.V., Narayanan, P.J.: Recognition of Malayalam Documents. In: Advances in Pattern Recognition, Guide to OCR for Indic Scripts. Springer, London (2009)Google Scholar
  9. 9.
    Pal, U., Chaudhuri, B.B.: Indian script character recognition: A survey. Pattern Recognition 37(9), 1887–1899 (2004)CrossRefGoogle Scholar
  10. 10.
    Rahman, A.F.R., Rahman, R., Fairhurst, M.C.: Recognition of handwritten Bengali characters: a novel multistage approach. Pattern Recognition (2002)Google Scholar
  11. 11.
    Shivsubramani, K., Loganathan, R., Srinivasan, C.J., Ajay, V., Soman, K.P.: Multiclass Hierarchical SVM for Recognition of Printed Tamil Characters. In: Proc. of IJCAI (2007)Google Scholar
  12. 12.
    Mori, S., Suen, C.Y., Yamamoto, K.: Historical Review of OCR Research and Development. Proceedings of the IEEE (1992), doi:10.1109/5.156468Google Scholar
  13. 13.
    Soman, K.P., Ramanathan, R.: Level Set Theory for Image Segmentation. In: Digital Signal and Image Processing- The Sparse Way. Isa Publishers (2012)Google Scholar
  14. 14.
    Soman, S.T., Soumya, V.J., Soman, K.P.: Singular Value Decomposition A Classroom Approach. International Journal of Recent Trends in Engineering 1(2) (2009)Google Scholar
  15. 15.
    Trier, D., Jain, A.K., Taxt, T.: Feature Extraction Methods for Character Recognition-A Survey. Pattern Recognition 29, 641–662 (1996)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Centre for Excellence in Computational Engineering and NetworkingAmrita School of EngineeringCoimbatoreIndia

Personalised recommendations