Optical character recognition of Gurmukhi script using multiple classifiers

ABSTRACT

In this paper, we present a robust and font independent Gurmukhi OCR system, which performs reasonably well on old documents as well. The OCR is based on four classifiers operating in serial and parallel mode. For combining the results of the classifiers operating in parallel mode, a corpus based weighted voting method is used. Combining multiple classifiers in such a way, that their individual weaknesses are compensated while their individual strengths are preserved, results in significantly better performance than what can be achieved with a single classifier. The problem of broken characters, which frequently appear in old documents, has also been tackled using a structural feature based algorithm.

References

1. Brill Eric and Jun Wu: Classifier Combination for Improved Lexical Disambiguation, Proceedings of the 17th international conference on Computational linguistics, vol. 1, pp. 191--195. Montreal, Quebec, Canada (1998).
2. Roli Fabio, Giacinto Giorgio, Vernazza Gianni: Methods for Designing Multiple Classifier Systems, Proceedings of the Second International Workshop on Multiple Classifier Systems, pp. 78--87. Springer-Verlag London, UK (2001).
3. Ludmila IK.,: A Theoretical Study on Six Classifier Fusion Strategies, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 24, No. 2, pp. 281--286, (2002.).
4. Kittler J., Hatef M., Duin RPW, Matas J.: On Combining Classifiers, IEEE Trans. On Pat. Analysis and Machine Intel., vol. 20, No. 3, pp. 226--239 (1998).
5. Prevost L., Michel-Sendis C., Moises A., Oudot L., Milgram M: Combining model-based and discriminative classifiers: application to handwritten character recognition, ICDAR'03 (2003).
6. Ke Chenl, Lanwang, Huisheng Chi: Methods of Combining Multiple Classifiers with Different Features and their Applications to Text-Independent Speaker Identification: International Journal of Pattern Recognition and Artificial Intelligence, Vol. 11, No. 3, pp. 417--445 (1997).
7. Lehal G. S., Singh Chandan,: A Complete Machine Printed Gurmukhi OCR System, Vivek, pp. 10--17, Vol. 16, No. 3. (2006).
8. Benedicte Allier, Nadia Bali, Hubert Emptoz: Automatic accurate broken character restoration for patrimonial documents. IJDAR 8(4), pp 246--261 (2006)
9. Billawala, N., Hart, P. E., Pearis, M.: Image continuation. In: Proceedings of the International Conference on Document Analysis and Recognition, pp. 53--57, Tsukuba, Japan (1993)
10. Shi, Z., Govindaraju, V.: Character image enhancement by selective region-growing. Pattern Recognit. Lett. (17), pp. 523--527 (1996)
11. Yu. D., Yan, H.: Reconstruction of broken handwritten digits based on structural morphological features. Pattern Recognit. (34), pp. 235--254 (2001).
12. Whichello, A., Yan, H.: Linking broken character borders with variable sized masks to improve recognition. Pattern Recognition 29(8), pp. 1429--1435 (1996)
13. Bhattacharya U., Chaudhuri B. B.: A Majority Voting Scheme for Multi resolution Recognition of Hand printed Numerals, ICDAR'03, pp. 16--20, 3--6 (2003).
14. Lam L., Suen, C. Y.,: Application of Majority Voting to Pattern Recognition: An Analysis of its Behaviour and Performance, IEEE Trans. on System Man and Cyebrn-Part A: Systems and Humans, vol. 27, pp. 553--568 (1997).

Index Terms

• Applied computing

  • Arts and humanities

    • Language translation

  • Document management and text processing

    • Document capture

      • Optical character recognition

• Computing methodologies

  • Artificial intelligence

    • Natural language processing

  • Machine learning

    • Learning paradigms

      • Supervised learning

        • Supervised learning by classification

    • Machine learning approaches

      • Classification and regression trees