Skip to main content
SpringerLink
Log in

An Implicit Segmentation Approach for Telugu Text Recognition Based on Hidden Markov Models

  • Conference paper
  • First Online:
Advances in Signal Processing and Intelligent Recognition Systems

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 425))

Abstract

Telugu text is composed of aksharas (characters). The presence of split and connected aksharas in Telugu document images causes segmentation difficulties and the performance of the Telugu OCR systems is affected. Our novel approach to solve this problem is using an implicit segmentation for recognizing words. The implicit segmentation approach does not need prior segmentation of the words into aksharas before they are recognized. Since the Hidden Markov models (HMM) are successfully applied for phoneme recognition with no prior segmentation of the speech into phonemes in the automatic speech recognition applications. In this paper, we report on the use of continuous density Hidden Markov Models for representing the shape of aksharas to build Telugu text recognition system. The sliding window method is used for computing simple statistical features and 450 akshara HMMs are trained. We use word bigram language model as contextual information. The word recognition relies on akshara models and contextual information of words. The word recognition involves finding the maximum likelihood sequence of akshara models that matches against the feature vector sequence. Our system recognizes words with split and connected aksharas. The performance of the system is encouraging.

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 169.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
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

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Aas, K., Eikvil, L., Andersen, T.: Text recognition from grey level images using hidden markov models. In: Hlaváč, V., Šára, R. (eds.) Computer Analysis of Images and Patterns. Lecture Notes in Computer Science, vol. 970, pp. 503–508. Springer, Heidelberg (1995)

    Chapter  Google Scholar 

  2. Bazzi, I., Schwartz, R., Makhoul, J.: An omnifont open-vocabulary ocr system for english and arabic. IEEE Transactions on Pattern Analysis and Machine Intelligence 21(6), 495–504 (1999)

    Article  Google Scholar 

  3. Bose, C., Kuo, S.S.: Connected and degraded text recognition using hidden markov model. In: Proceedings of the 11th IAPR International Conference on Pattern Recognition, 1992, Conference B: Pattern Recognition Methodology and Systems, vol. II, pp. 116–119 (1992)

    Google Scholar 

  4. Dutta, S., Sankaran, N., Sankar, K., Jawahar, C.: Robust recognition of degraded documents using character n-grams. In: 2012 10th IAPR International Workshop on Document Analysis Systems (DAS), pp. 130–134 (2012)

    Google Scholar 

  5. Elms, A.: A connected character recogniser using level building of hmms. In: Proceedings of the 12th IAPR International Conference on Pattern Recognition, 1994, Conference B: Computer Vision amp; Image Processing, vol. 2, pp. 439–441 (1994)

    Google Scholar 

  6. Elms, A., Procter, S., Illingworth, J.: The advantage of using an hmm-based approach for faxed word recognition. International Journal on Document Analysis and Recognition 1(1), 18–36 (1998)

    Article  Google Scholar 

  7. Khorsheed, M.S.: Offline recognition of omnifont arabic text using the hmm toolkit (htk). Pattern Recogn. Lett. 28(12), 1563–1571 (2007)

    Article  Google Scholar 

  8. Krishnan, P., Sankaran, N., Singh, A., Jawahar, C.: Towards a robust OCR system for indic scripts. In: 2014 11th IAPR International Workshop on Document Analysis Systems (DAS), pp. 141–145 (2014)

    Google Scholar 

  9. Kumar, P.P., Bhagvati, C., Agarwal, A.: On performance analysis of end-to-end OCR systems of indic scripts. In: Proceeding of the Workshop on Document Analysis and Recognition, pp. 132–138. ACM, New York (2012)

    Google Scholar 

  10. Natarajan, P., MacRostie, E., Decerbo, M.: The BBN byblos hindi OCR system. In: Govindaraju, V., Setlur, S.R. (eds.) Guide to OCR for Indic Scripts, Advances in Pattern Recognition, pp. 173–180. Springer, London (2010)

    Google Scholar 

  11. Negi, A., Bhagvati, C., Krishna, B.: An OCR system for telugu. In: ICDAR, pp. 1110–1114. IEEE Computer Society (2001)

    Google Scholar 

  12. Rabiner, L.: A tutorial on hidden markov models and selected applications in speech recognition. Proceedings of the IEEE 77(2), 257–286 (1989)

    Article  Google Scholar 

  13. Roy, P., Roy, S., Pal, U.: Multi-oriented text recognition in graphical documents using hmm. In: 2014 11th IAPR International Workshop on Document Analysis Systems (DAS), pp. 136–140 (2014)

    Google Scholar 

  14. Tesseract: http://code.google.com/p/tesseract-ocr/

  15. Young, S.: The HTK Hidden Markov Model Toolkit: Design and Philosophy (1993)

    Google Scholar 

  16. Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Liu, X.A., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., Woodland, P.: The HTK Book (for HTK Version 3.4). Cambridge University Engineering Department (2006)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Information Technology, Mahatma Gandhi Institute of Technology, Hyderabad, India

    D. Koteswara Rao

  2. School of Computer and Information Sciences, University of Hyderabad, Hyderabad, India

    D. Koteswara Rao & Atul Negi

Authors
  1. D. Koteswara Rao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Atul Negi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to D. Koteswara Rao .

Editor information

Editors and Affiliations

  1. and Management – Kerala (IIITM-K), Indian Inst. of Information Technology, Trivandrum, Kerala, India

    Sabu M. Thampi

  2. Machine Intelligence Unit, Indian Statistical Institute, Kolkata, West Bengal, India

    Sanghamitra Bandyopadhyay

  3. Department of Electrical, Ryerson University, Toronto, Ontario, Canada

    Sri Krishnan

  4. Providence University, Taichung, Taiwan

    Kuan-Ching Li

  5. Computer Engineering Department, Vladimir State University, Vladimir Region, Russia

    Sergey Mosin

  6. School of Electrical, Nanyang Technological University, Singapore, Singapore

    Maode Ma

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this paper

Cite this paper

Koteswara Rao, D., Negi, A. (2016). An Implicit Segmentation Approach for Telugu Text Recognition Based on Hidden Markov Models. In: Thampi, S., Bandyopadhyay, S., Krishnan, S., Li, KC., Mosin, S., Ma, M. (eds) Advances in Signal Processing and Intelligent Recognition Systems. Advances in Intelligent Systems and Computing, vol 425. Springer, Cham. https://doi.org/10.1007/978-3-319-28658-7_54

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-28658-7_54

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-28656-3

  • Online ISBN: 978-3-319-28658-7

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation