Recognition of Simple and Conjunct Handwritten Malayalam Characters Using LCPA Algorithm

  • M. Abdul Rahiman
  • M. S. Rajasree
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 192)


This paper mainly focuses on the recognition of both simple and conjunct handwritten characters in Malayalam, a South Indian language. The algorithm proposed recognizes these characters mainly based on the strokes and lines contained in them. Here the input is an image of handwritten Malayalam characters, which undergoes different phases of processing to produce an editable document of Malayalam characters in a predefined format as output. In this paper, detailed description of the methods for character identification is given. The whole OCR process is presented in three different modules: Pre-processing, Skeletonization and Recognition. In Pre-processing, the input image is scanned and subjected to line and character separation. In Skeletonization, the digital image is transformed into a set of original components. In Recognition, the characters are classified based on their features. The feature extraction of the characters is done by the analyzing the position and count of the horizontal and vertical lines. A classification of the simple and conjunct characters is also devised based on the count and position of the horizontal and vertical lines which make up those characters.


Malayalam Optical Character Recognition Feature Extraction Wavelet Transform Neural Networks HLH Patterns 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Trier, D., Jain, A.K., Taxt, T.: Feature Extraction methods for Character Recognition – A Survey. Pattern Recognition 29, 641–662 (1996)CrossRefGoogle Scholar
  2. 2.
    Srihari, S.N., Yang, X., Ball, G.R.: Offline Chinese Handwriting Recognition: an assessment of current Technology. Front. Computer Science 1(2), 137–155 (2007)CrossRefGoogle Scholar
  3. 3.
    Amin, A.: Recognition of Printed Arabic Text based on global features and Decision Tree Learning Techniques. Pattern Trcognition 33(8), 1309–1323 (2000)CrossRefGoogle Scholar
  4. 4.
    Pal, U., Chaudhuri, B.B.: Printed Devanagari script OCR System. Vivek  10 (1997)Google Scholar
  5. 5.
    Chaudhuri, B., Pal, U., Mitra, U.: Automatic recognition of printed Oriya script. Sadhana 27, Part 1, 23–34 (2002)CrossRefGoogle Scholar
  6. 6.
    Seethalakshmi, R., Sreeranjani, T.R., Balachandar, T., Singh, A., Singh, M., Ratan, R., Kumar, S.: Optical Character Recognition for printed Tamil text using Unicode. Journal of Zhejiang University SCI 6A(11), 1297–1305 (2005)CrossRefGoogle Scholar
  7. 7.
    Lakshmi, C.V., Patvardhan, C.: A multi-font OCR system for printed Telugu text. In: Proc. of Language Engineering Conference LEC, Hyderabad, pp. 7–17 (2002)Google Scholar
  8. 8.
    Ashwin, T.V., Sastry, P.S.: A font and size independent OCR system for printed Kannada documents using support vector machines. Saadhana 27, Part 1, 35–58 (2002)CrossRefGoogle Scholar
  9. 9.
    Abdul Rahiman, M., Rajasree, M.S.: Printed Malayalam Character Recognition Using Back propagation Neural Networks. In: Proc. of IEEE International Advance Computing Conference (IACC 2009), Patiala, pp. 1140–1144 (March 2009)Google Scholar
  10. 10.
    Journal of Language Technology, Viswabharat@tdil (July 2003)Google Scholar
  11. 11.
    Anuradha, Koteswarra, B.: An efficient Binarization technique for old documents. In: Proc. of International Conference on Systemics, Cybernetics and Inforrmatics, Hyderabad, pp. 771–775 (2006)Google Scholar
  12. 12.
    Chaudhuri, B.B., Pal, U.: Skew Angle Detection of Digitized Indian Script Document. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(2) (February 1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • M. Abdul Rahiman
    • 1
  • M. S. Rajasree
    • 2
  1. 1.Karpagam UniversityCoimbatoreIndia
  2. 2.Govt. College of EnggTrivandrumIndia

Personalised recommendations