Printed Odia Digit Recognition Using Finite Automaton

  • Ramesh Kumar Mohapatra
  • Banshidhar Majhi
  • Sanjay Kumar Jena
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 43)


Odia digit recognition (ODR) is one of the intriguing areas of research topic in the field of optical character recognition. This communication is an attempt to recognize printed Odia digits by considering their structural information as features and finite automaton with output as recognizer. The sample data set is created for Odia digits, and we named it as Odia digit database (ODDB). Each image is passed through several precompiled standard modules such as binarization, noise removal, segmentation, skeletonization. The image thus obtained is normalized to a size of 32 × 32 2D image. Chain coding is used on the skeletonised image to retrieve information regarding number of end points, \(T\)-joints, \(X\)-joints and loops. It is observed that finite automaton is able to classify the digits with a good accuracy rate except the digits Open image in new window . We have used the correlation function to distinguish between, Open image in new window . For our experiment we have considered some poor quality degraded printed documents. The simulation result records 96.08 % overall recognition accuracy.


ODR Finite automaton Correlation Chain coding 


  1. 1.
    Trier, Ø.D., Jain, A.K., Taxt, T.: Feature extraction methods for character recognition-a survey. Pattern Recogn. 29(4), 641–662 (1996)CrossRefGoogle Scholar
  2. 2.
    Pal, U., Chaudhuri, B.B.: Indian script character recognition: a survey. Pattern Recogn. 37(9), 1887–1899 (2004)CrossRefGoogle Scholar
  3. 3.
    Nikolaou, N., Makridis, M., Gatos, B., Stamatopoulos, N., Papamarkos, N.: Segmentation of historical machine-printed documents using adaptive run length smoothing and skeleton segmentation paths. Image Vis. Comput. 28(4), 590–604 (2010)CrossRefGoogle Scholar
  4. 4.
    Akiyama, T., Hagita, N.: Automated entry system for printed documents. Pattern Recogn. 23(11), 1141–1154 (1990)CrossRefGoogle Scholar
  5. 5.
    Chaudhuri, B.B., Pal, U.: A complete printed Bangla OCR system. Pattern Recogn. 31(5), 531–549 (1998)CrossRefGoogle Scholar
  6. 6.
    Chaudhuri, B.B., Pal, U., Mitra, M.: Automatic recognition of printed Oriya script. Sadhana 27(1), 23–34 (2002)CrossRefGoogle Scholar
  7. 7.
    Louloudis, G., Gatos, B., Pratikakis, I., Halatsis, C.: Text line and word segmentation of handwritten documents. New Frontiers in handwriting recognition. Pattern Recogn. 42(12), 3169–3183 (2009)MATHCrossRefGoogle Scholar
  8. 8.
    Zingaretti, P., Gasparroni, M., Vecci, L.: Fast chain coding of region boundaries. IEEE Trans. Pattern Anal. Mach. Intell. 20(4), 407–415 (1998)Google Scholar
  9. 9.
    Cruz, H.S., Bribiesca, E., Dagnino, R.M.R.: Efficiency of chain codes to represent binary objects. Pattern Recogn. 40(6), 1660–1674 (2007)MATHCrossRefGoogle Scholar
  10. 10.
    MATLAB. version 7.10.0 (R2010a). The MathWorks Inc., Natick, Massachusetts (2012)Google Scholar

Copyright information

© Springer India 2016

Authors and Affiliations

  • Ramesh Kumar Mohapatra
    • 1
  • Banshidhar Majhi
    • 1
  • Sanjay Kumar Jena
    • 1
  1. 1.Department of Computer Science and EngineeringNational Institute of TechnologyRourkelaIndia

Personalised recommendations