Advertisement

Off-line Odia Handwritten Character Recognition: A Hybrid Approach

  • Abhisek Sethy
  • Prashanta Kumar Patra
  • Deepak Ranjan Nayak
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 490)

Abstract

Optical character recognition (OCR) is one of the most popular and challenging topic of pattern recognition with a wide range of applications in various fields. This paper proposes an OCR system for Odia scripts which comprises of three stages, namely preprocessing, feature extraction, and classification. In the preprocessing stage, we have employed median filtering on the input image and subsequently we have applied normalization and skeletonization methods over images for extraction of boundary edge pixel points. In the feature extraction stage, initially the image is divided into 3 × 3 grids and the corresponding centroids for all the nine zones are evaluated. Thereafter, we have drawn the horizontal and vertical symmetric projection to the nearest pixel of the image which is dubbed as binary external symmetry axis constellation for unconstrained handwritten character. From which we have calculated the horizontal and vertical Euclidean distance for the same nearest pixel from centroid of each zone. Then we have calculated the mean Euclidean distance as well as the mean angular values of the zones. This is considered as the key feature values of our proposed system. Lastly, both kernel support vector machine (KSVM) and quadratic discriminant classifier (QDA) have been separately used as the classifier. To validate the proposed system, a series of experiments have been carried out on a standard database as NIT Rourkela Odia Database. From the database, we select 200 samples from each of the 47 categories. Simulation results based on a tenfold cross-validation approach indicate that the proposed system offers better recognition accuracy then other competent schemes. Moreover, the recognition accuracy obtained by KSVM and QDA classifier is 96.5 and 97.4%, respectively.

Keywords

Optical character recognition Feature vector BESAC KSVM QDA 

Notes

Acknowledgements

The authors are sincerely thankful to the Department of Computer Science and Engineering, College of Engineering and Technology, Bhubaneswar. And we are also thankful to all the authors of references.

References

  1. 1.
    Govindan VK, Shivaprasad AP (1990) Character recognition—a review. Pattern Recogn 23Google Scholar
  2. 2.
    Mantas J (1986) An overview of character recognition methodologies. Pattern Recogn 19:425–430CrossRefGoogle Scholar
  3. 3.
    Plamondon R, Srihari SN (2000) On-line and off-line handwritten recognition: a comprehensive survey. IEEE Trans PAMI 22Google Scholar
  4. 4.
    Pal U, Chaudhuri BB (2004) Indian script character recognition: a survey. Pattern Recogn 37Google Scholar
  5. 5.
    Dash KS, Puhan NB, Panda G (2016) Odia character recognition: a direction review. Artif Intell RevGoogle Scholar
  6. 6.
    Patra PK, Nayak M, Nayak SK, Gabbak NK (2002) Probabilistic neural network for pattern classification. In: Proceeding of the international joint conference on neural networks, May 12–17, HawaiiGoogle Scholar
  7. 7.
    Pal U, Wakabayashi T, Kimura F (2005) A system for off-line Oriya handwritten character recognition using curvature feature. In: IEEE proceeding of the 10th international conference on information technology, September 21–23, ChinaGoogle Scholar
  8. 8.
    Chaudhuri BB, Pal U, Mitra M (2001) Automatic recognition of printed Oriya script. In: IEEE proceeding of the sixth international conference on document analysis and recognition, September 10–13, Washington, USAGoogle Scholar
  9. 9.
    Padhi D, Senapati D (2015) Zone centroid distance and standard deviation based feature matrix for Odia handwritten character recognition. In: Proceeding of the international conference on frontiers of intelligent computing theory and applications, November 16–18, Kolkata, IndiaGoogle Scholar
  10. 10.
    Pujari AK, Mitra C, Mishra S (2014) A new parallel thinning algorithm with stroke correction for Odia characters. Advanced computing, networking and informatics. Springer International Publishing SwitzerlandGoogle Scholar
  11. 11.
    Mitra C, Pujari AK (2013) Directional decomposition for Odia character recognition, mining intelligence and knowledge exploration. In: Proceeding in lecture notes in computer science, vol 8284. Springer, BerlinGoogle Scholar
  12. 12.
    Nayak DR, Dash R, Majhi B, Mohammed J (2016) Non-linear cellular automata based edge detector for optical character images. Simul Trans Soc Model Simul Int 1–11Google Scholar
  13. 13.
    Sethy A, Patra PK, Nayak DR (2016) Off-line Odia handwritten character recognition using DWT and PCA. In: Proceeding in international conference on advanced computing and intelligent engineering, December 21–23, Bhubaneswar, IndiaGoogle Scholar
  14. 14.
    Dash KS, Puhan NB, Panda G (2016) BESAC: binary external symmetry axis constellation for unconstrained handwritten character recognition. Pattern Recogn LettGoogle Scholar
  15. 15.
    Mishra TK, Majhi B, Sa PK, Panda S (2014) Model based Odia numeral recognition using fuzzy aggregated features. Frontiers of Computer Science. Springer, BerlinGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Abhisek Sethy
    • 1
  • Prashanta Kumar Patra
    • 1
  • Deepak Ranjan Nayak
    • 2
  1. 1.Department of Computer Science and EngineeringCollege of Engineering and Technology BhubaneswarBhubaneswarIndia
  2. 2.Department of Computer Science and EngineeringNational Institute of Technology RourkelaRourkelaIndia

Personalised recommendations