Skip to main content
SpringerLink
Log in

Discrete Cosine Transform-Based Feature Selection for Marathi Numeral Recognition System

  • Conference paper
  • First Online:
Advances in Computer Communication and Computational Sciences

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 760))

Abstract

Optical character recognition system is hotcake for the researchers since last four decades. Recognition of handwritten Devanagari characters and digits is comparatively a tough task as compared to recognition other scripts like English or Latin. In this manuscript, a novel feature extraction and selection method is proposed for the recognition of isolated handwritten Marathi numbers based on one-dimensional Discrete Cosine Transform (1-D DCT) algorithm for reducing the dimensionality of feature space. The scanned document is preprocessed and segmented to create isolated numerals. Features for each numeral can be calculated after normalizing the numeral image to 32 × 32 size. Based on these reduced features, the numerals are classified into appropriate groups. Database of 6000 numerals size is used for the proposed work. Neural network is used for classification of numerals based on the extracted and selected features. Experimental results show accuracy observed for the method is 90.30%.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Roy, K., Vaidya, S., Pal, U., Chaudhuri, B.B., Belaid, A.: A system for indian postal automation. In: Proceedings of the 8th International Conference Document Analysis and Recognition, Seoul, Korea, pp. 1060–1064 (2005)

    Google Scholar 

  2. Wen, Y., Lu, Y., Shi, P.F.: Handwritten Bangla numeral recognition system and its application to postal automation. Pattern Recogn. 40(1), 99–107 (2007)

    Google Scholar 

  3. Pal, U., Chaudhari, B.: Indian script character recognition: a survey. Pattern Recogn. 37, 1887–1899 (2004)

    Article  Google Scholar 

  4. Jayadevan R., Kolhe, S.R., Patil, P.M, Pal, U.: Offline recognition of devanagari script: a survey. IEEE Trans. Syst. Man, and Cybern. Part C (Appl. Rev.) 41(6), 782–796 (2011)

    Google Scholar 

  5. Das, N., Reddy, J.M., Sarkar, R., Basu, S., Kundu, M., Nasipuri, M., Basu, D.K.: A statistical–topological feature combination for recognition of handwritten numerals. J. Appl. Soft Comput. 12, 2486–2495 (2012)

    Article  Google Scholar 

  6. Vaidya, M., Joshi, Y.V.: Marathi Numeral Recognition using statistical distribution features. In: Proceedings of the IEEE Conference on Information Processing, pp. 586–591 (2015)

    Google Scholar 

  7. Vaidya, M., Joshi, Y.V: Handwritten numeral identification system using pixel level distribution features. In: Proceedings of the 2nd International Conference on Information and Communication Technology for Intelligent Systems, vol. 2, pp. 307–315 (2017)

    Google Scholar 

  8. Pal, U., Chaudhuri, B.B.: Automatic recognition of unconstrained off-line Bangla handwritten numerals. In: Advances in Multimodal Interfaces—ICMI 2000, pp. 371–378. Springer, Berlin, Heidelberg (2000)

    Google Scholar 

  9. Tripathy, N., Panda, M., Pal, U.: System for Oriya handwritten numeral recognition. In: Proceedings of the Imaging International Society for Optics and Photonics, pp. 174–181 (2003)

    Google Scholar 

  10. Rajput G., Hangarge, M.: Recognition of isolated handwritten Kannada numerals based on image fusion method. Pattern Recogn. Mach. Intell. 153–160 (2007)

    Google Scholar 

  11. Fan, Z., Queiroz, R.: Maximum likelihood estimation of JPEG quantization table in the identification of bitmap compression history. In: Proceedings of the IEEE International Conference on of Image Processing 2000, vol. 1, pp. 948–951 (2000)

    Google Scholar 

  12. Ahmed, N., Natarajan, T., Rao, K.R.: Discrete cosine transform. IEEE Trans. Comput. C-25, 90–93 (1974)

    Google Scholar 

  13. Plamondon, R., Srihari, S.N.: On-line and off-line hand-writing recognition: a comprehensive survey. IEEE Trans. Pattern Anal. Mach. Intell. 22(1), 63–84 (2000)

    Article  Google Scholar 

  14. Bhattacharya, U., Chaudhuri, B.B.: Handwritten numeral databases of Indian scripts and multistage recognition of mixed numerals. IEEE Trans. Pattern Recogn. Mach. Intell. 31(3), 444–457 (2009)

    Article  Google Scholar 

  15. Garain, U., Chaudhuri, B.B.: Segmentation of touching characters in printed devnagari and bangla scripts using fuzzy multifactorial analysis. IEEE Trans. Syst. Man Cybern. Part C Appl. Rev. vol. 32, no. 4, pp. 449–459, 2002

    Google Scholar 

  16. Han, J., Pei, J., Kamber, M.: Data Mining: Concepts and Techniques. Elsevier (2011)

    Google Scholar 

  17. Shaw, B., Parui, S.K., Shridhar, M.: Offline handwritten Devanagari word recognition: a segmentation based approach. In: Proceedings of the International Conference on Pattern Recognition (ICPR), Tampa, Florida, USA, pp. 1–4 (2008)

    Google Scholar 

  18. Lu, Z., Chi, Z., Siu, W.: Extraction and optimization of B-spline PBD templates for recognition of connected handwritten digit strings. IEEE Trans. Pattern Anal. Mach. Intell. 24(1), 132–139 (2002)

    Article  Google Scholar 

  19. Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1), 62–66 (1979)

    Article  MathSciNet  Google Scholar 

  20. Aburas A., Rehiel, S.A.: JPEG for Arabic handwritten character recognition: add a dimension of application. In: Advances in Robotics, Automation and Control, InTech, pp. 21–32 (2008)

    Google Scholar 

  21. Birajdar, G., Subhedar, M.: Use of JPEG algorithm in handwritten Devanagari numeral recognition. Int. J. Distrib. Parallel Syst. 2(4), 152–160 (2011)

    Google Scholar 

  22. Reddy, G.S., Sharma, P., Prasanna, S.R.M., Mahanta, C., Sharma, L.N.: Combined online and offline assamese handwritten numeral recognizer. In: Proceedings of the IEEE National Conference on Communications, pp. 1–5 (2012)

    Google Scholar 

  23. Mishra, T.K., Majhi, B., Panda. S.: A comparative analysis of image transformations for handwritten Odia numeral recognition. In: Proceedings of the IEEE International Conference on Advances in Computing, Communications and Informatics (2013)

    Google Scholar 

  24. Lwin, T.N., Soe, T.: Comparison of handwriting characters accuracy using different feature extraction methods. Int. J. Sci. Eng. Technol. Res. 3(6), 1027–1032 (2014)

    Google Scholar 

  25. Sethy, A., Patra, P.K.: Off-line Odia handwritten numeral recognition using neural network: a comparative analysis. In: Proceedings of the IEEE International Conference on Computing, Communication and Automation, pp. 1099–1103 (2016)

    Google Scholar 

Download references

Acknowledgements

The authors acknowledge their thanks to Umapada Pal, Indian Institute of Statistics, Kolkata, and Vikas Dongre for providing the databases support for the experimentation.

Author information

Authors and Affiliations

  1. Shri Guru Gobind Singhji Institute of Engineering and Technology, Vishnupuri, Nanded, Maharashtra, India

    Madhav Vaidya, Yashwant Joshi, Milind Bhalerao & Ganesh Pakle

Authors
  1. Madhav Vaidya
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yashwant Joshi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Milind Bhalerao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ganesh Pakle
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Madhav Vaidya .

Editor information

Editors and Affiliations

  1. Department of Mathematics & Computer Science, University of Missouri, St. Louis, Missouri, USA

    Sanjiv K. Bhatia

  2. Computer Science Engineering Department, ABES Engineering College, Ghaziabad, India

    Shailesh Tiwari

  3. Department of Computer Science & Engineering, Motilal Nehru National Institute of Technology, Allahabad, Uttar Pradesh, India

    Krishn K. Mishra

  4. Department of Computer Science & Engineering, ABES Engineering College, Ghaziabad, India

    Munesh C. Trivedi

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Vaidya, M., Joshi, Y., Bhalerao, M., Pakle, G. (2019). Discrete Cosine Transform-Based Feature Selection for Marathi Numeral Recognition System. In: Bhatia, S., Tiwari, S., Mishra, K., Trivedi, M. (eds) Advances in Computer Communication and Computational Sciences. Advances in Intelligent Systems and Computing, vol 760. Springer, Singapore. https://doi.org/10.1007/978-981-13-0344-9_30

Download citation

Publish with us

Policies and ethics

Search

Navigation