Skip to main content
SpringerLink
Log in
SpringerLink
Log in

Introduction

  • Chapter
  • First Online:
Markov Models for Handwriting Recognition

Part of the book series: SpringerBriefs in Computer Science ((BRIEFSCOMPUTER))

  • 1006 Accesses

Abstract

Reading systems, i.e., machines that try to recreate the human capabilities of reading printed or handwritten script, are of fundamental scientific and commercial interest. They play a major role in a number of application domains including, for example, document analysis (mail sorting, bank check processing, archiving), and innovative human-computer interfaces (pen based input). Similar to, for example, spoken language, handwritten script corresponds to sequential data, which requires specialized analysis techniques that can cope with segmentation and classification in a reasonable manner. Markov models represent a well suited framework for the analysis of sequential data in general, and for processing handwritten script in particular. Already introduced about a century ago, in the last few decades they gained popularity also for handwriting recognition. Especially hidden Markov models in combination with Markov chain—i.e., n-gram—models have been employed very successfully for a number of applications of both online and offline handwriting recognition. This book gives an overview of theoretical concepts as well as practical aspects of Markov model based handwriting recognition.

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 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
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

Notes

  1. 1.

    Time-delay neural networks (TDNNs) were proposed for automatic speech recognition in [7] and first applied to an online handwriting recognition task in [8].

  2. 2.

    Interestingly techniques for the recognition of Latin and Arabic script are more similar than one might expect when only visually comparing documents written in, e.g., English or an Arabic language [14].

References

  1. Arica N, Yarman-Vural FT (2001) An overview of character recognition focused on off-line handwriting. IEEE Trans on Syst Man Cybern Part C Appl Rev 31(2):216–232

    Article  Google Scholar 

  2. Bunke H (2003) Recognition of cursive Roman handwriting—Past, present and future. In: Proceedings of international conference on document analysis and recognition, Edinburgh, Scotland, vol 1, pp 448–459

    Google Scholar 

  3. Fujisawa H (2008) Forty years of research in character and document recognition—an industrial perspective. Pattern Recognit 41:2435–2446

    Article  Google Scholar 

  4. Plamondon R, Srihari SN (2000) On-line and off-line handwriting recognition: a comprehensive survey. IEEE Trans on Pattern Anal and Mach Intell 22(1):63–84

    Article  Google Scholar 

  5. Vinciarelli A (2002) A survey on off-line cursive word recognition. Pattern Recognit 35:1433–1446

    Article  MATH  Google Scholar 

  6. Pittman JA (2007) Handwriting recognition: tablet PC text input. IEEE Comput 40(9):49–54

    Google Scholar 

  7. Lang KJ, Waibel AH, Hinton GE (1990) A time-delay neural network architecture for isolated word recognition. Neural Netw 3(1):23–43

    Article  Google Scholar 

  8. Guyon I, Albrecht P, Le Cun Y, Denker J, Hubbard W (1991) Design of a neural network character recognizer for a touch terminal. Pattern Recognit 24:105–119

    Article  Google Scholar 

  9. Davis R (2007) Magic paper: sketch-understanding research. IEEE Comput 40(9):34–41

    Google Scholar 

  10. El Abed H, Märgner V (2011) ICDAR 2009—Arabic handwriting recognition competition. Int J Document Anal Recognit 14:3–13

    Article  Google Scholar 

  11. Mondal T, Bhattacharya U, Parui S, Das K, Mandalapu D (2010) On-line handwriting recognition of Indian scripts—The first benchmark. In: Proceedings of the international conference on frontiers in handwriting recognition, Kolkata, India, pp 200–205

    Google Scholar 

  12. Jaeger S, Liu CL, Nakagawa M (2003) The state of the art in Japanese online handwriting recognition compared to techniques in western handwriting recognition. Int J Document Anal Recognit 6:75–8

    Article  Google Scholar 

  13. Liu CL, Jaeger S, Nakagawa M (2004) Online recognition of Chinese characters: the state- of-the-art. IEEE Trans Pattern Anal Mach Intell 26(2):198–213

    Article  Google Scholar 

  14. Schambach MP, Rottland J, Alary T (2008) How to convert a Latin handwriting recognition system to Arabic. In: Proceedings of the international conference on frontiers in handwriting recognition, Montréal, Canada

    Google Scholar 

  15. Markov AA (1913) Example of statistical investigations of the text of ,,Eugen Onegin", wich demonstrates the connection of events in a chain. In: Bulletin de l’Académie Impériale des Sciences de St.-Pétersbourg, Sankt-Petersburg, Russia, pp 153–162 (in Russian)

    Google Scholar 

  16. Baum L, Petrie T (1966) Statistical inference for probabilistic functions of finite state Markov chains. Ann Math Statist 37:1554–1563

    Article  MathSciNet  MATH  Google Scholar 

  17. Baum L, Petrie T, Soules G, Weiss N (1970) A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. Ann Math Statist 41:164–171

    Article  MathSciNet  MATH  Google Scholar 

  18. Viterbi A (1967) Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE Trans Inf Theory 13:260–269

    Article  MATH  Google Scholar 

  19. Young S (1996) A review of large-vocabulary continuous-speech recognition. IEEE Signal Process Mag 13(9):45–57

    Article  Google Scholar 

  20. Kaltenmeier A, Caesar T, Gloger JM, Mandler E (1993) Sophisticated topology of hidden Markov models for cursive script recognition. In: Proceedings of the international conference on document analysis and recognition, Tsukuba Science City, Japan, pp 139–142

    Google Scholar 

  21. Schwartz R, LaPre C, Makhoul J, Raphael C, Zhao Y (1996) Language-independent OCR using a continuous speech recognition system. In: Proceedings of the international conference on pattern recognition, Vienna, Austria, vol 3, pp 99–103

    Google Scholar 

  22. Vinciarelli A, Bengio S, Bunke H (2004) Offline recognition of unconstrained handwritten texts using HMMs and statistical language models. IEEE Trans Pattern Anal Mach Intell 26(6):709–720

    Article  Google Scholar 

  23. Britto AdS, Sabourin R, Bortolozzi F, Suen CY (2001) A two-stage HMM-based system for recognizing handwritten numeral strings. In: Proceedings of the international conference on document analysis and recognition, Seattle, USA, pp 396–400

    Google Scholar 

  24. Gauthier N, Artières T, Dorizzi B, Ballinari P (2001) Strategies for combining on-line and off-line information in an on-line handwriting recognition system. In: Proceedings of the international conference on document analysis and recognition, Seattle, USA, pp 412–416

    Google Scholar 

  25. Ge Y, Huo Q (2002) A study on the use of CDHMM for large vocabulary offline recognition of handwritten Chinese characters. In: Proceedings of the international workshop on frontiers in handwriting recognition, Niagara on the Lake, Canada, pp 334–338

    Google Scholar 

  26. Nopsuwanchai R, Biem A, Clocksin WF (2006) Maximization of mutual information for offline Thai handwriting recognition. IEEE Trans Pattern Anal Mach Intell 28(8):1347–1351

    Article  Google Scholar 

  27. Liwicki M, Bunke H (2008) Recognition of whiteboard notes: online, offline and combination. Machine Perception and Artificial Intelligence. World Scientific Publishing Company, Singapore

    Google Scholar 

  28. Plötz T, Thurau C, Fink GA (2008) Camera-based whiteboard reading: New approaches to a challenging task. In: Proceedings of the international conference on frontiers in handwriting recognition, Montreal, Canada, pp 385–390

    Google Scholar 

  29. Vajda S, Plötz T, Fink GA (2009) Layout analysis for camera-based whiteboard notes. J Univers Comput Sci 15(18):3307–3324

    Google Scholar 

  30. Wienecke M, Fink GA, Sagerer G (2003) Towards automatic video-based whiteboard reading. In: Proceedings of the international conference on document analysis and recognition, IEEE, Edinburgh, Scotland, pp 87–91

    Google Scholar 

  31. Wienecke M, Fink GA, Sagerer G (2005) Toward automatic video-based whiteboard reading. Int J Document Anal Recognit 7(2–3):188–200

    Article  Google Scholar 

  32. Fierrez J, Ortega-Garcia J, Ramos D, Gonzalez-Rodriguez J (2007) HMM-based on-line signature verification: feature extraction and signature modeling. Pattern Recognit Lett 28(16):2325–2334

    Article  Google Scholar 

  33. Bao LV, Garcia-Salicetti S, Dorizzi B (2007) On using the Viterbi path along with HMM likelihood information for online signature verification. IEEE Trans Syst Man Cybern Part B Cybern 37(5):1237–1247

    Article  Google Scholar 

  34. Brakensiek A, Rottland J, Rigoll G (2002) Handwritten address recognition with open vocabulary using character n-grams. In: Proceedings of the international workshop on frontiers in handwriting recognition, Niagara on the Lake, Canada, pp 357–362

    Google Scholar 

  35. Koerich AL, Leydier Y, Sabourin R, Suen CY (2002) A hybrid large vocabulary handwritten word recognition system using neuronal networks with hidden Markov models. In: Proceedings of the international workshop on frontiers in handwriting recognition, Niagara on the Lake, Canada, pp 99–104

    Google Scholar 

  36. Pechwitz M, Märgner V (2003) HMM based approach for handwritten Arabic word recognition using the IFN/ENIT-database. In: Proceedings of the international conference on document analysis and recognition, Edinburgh, Scotland, vol 2, pp 890–894

    Google Scholar 

  37. Vajda S, Belaid A (2005) Structural information implant in a context based segmentation-free HMM handwritten word recognition system for Latin and Bangla scripts. In: Proceedings of the international conference on document analysis and recognition, Seoul, Korea, vol 2, pp 1126–1130

    Google Scholar 

  38. Miletzki U, Bayer T, Schäfer H (1999) Continuous learning systems: postal address readers with built-in learning capability. In: Proceedings of the international conference on document analysis and recognition, Bangalore, India, pp 329–332

    Google Scholar 

  39. Schambach MP (2005) Fast script word recognition with very large vocabulary. In: Proceedings of the international conference on document analysis and recognition, Seoul, Korea, vol 1, pp 9–13

    Google Scholar 

  40. Morita M, El Yacoubi A, Sabourin R, Bortolozzi F, Suen CY (2001) Handwritten month word recognition on Brazilian bank cheques. In: Proceedings of the international conference on document analysis and recognition, Seattle, USA, pp 972–976

    Google Scholar 

  41. Xu Q, Kim JH, Lam L, Suen CY (2002) Recognition of handwritten month words on bank cheques. In: Proceedings of the international workshop on Frontiers in handwriting recognition, Niagara on the Lake, Canada, pp 111–116

    Google Scholar 

  42. Coetzer J, Herbst BM, du Preez JA (2004) Offline signature verification using the discrete Radon transform and a hidden Markov models. EURASIP J Appl Signal Process 4:559–571

    Google Scholar 

  43. Coetzer J, Herbst BM, du Preez JA (2006) Off-line signature verification: A comparison between human and machine performance. In: Proceedings of the international workshop on frontiers in handwriting recognition, La Baule, France, pp 481–486

    Google Scholar 

  44. Justino EJR, El Yacoubi A, Bortolozzi F, Sabourin R (2000) An off-line signature verification system using hidden Markov model and cross-validation. In: Proceedings of XIII Brazilian symposium on computer graphics and image processing, Gramado, Brazil, pp 105–112

    Google Scholar 

  45. Marti UV, Bunke H (2001b) Text line segmentation and word recognition in a system for general writer independent handwriting recognition. In: Proceedings of the international conference document analysis and recognition, Seattle, USA, pp 159–163

    Google Scholar 

  46. Zimmermann M, Bunke H (2002a) Automatic segmentation of the IAM off-line database for handwritten English text. In: Proceedings of the international conference on pattern recognition, Montréal, Canada, vol 4, pp 35–39

    Google Scholar 

  47. Chen M, Ding X, Wu Y (2003) Unified HMM-based layout analysis framework and algorithm. Sci China Ser F Inf Sci 46:401–408 10.1360/02yf0135

    Article  Google Scholar 

  48. e Silva A (2009) Learning rich hidden Markov models in document analysis: table location. In: Proceedings of the international conference on document analysis and recognition, Barcelona, Spain, pp 843–847

    Google Scholar 

  49. Zou J, Le D, Thoma GR (2007) Online medical journal article layout analysis. In: Lin X, Yanikoglu BA (eds) Document recognition and retrieval XIV, SPIE

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Culture Lab, School of Computing Science, Newcastle University, Grand Assembly Rooms, King’s Walk, Newcastle upon Tyne, NE1 7RU, UK

    Thomas Plötz

  2. Department of Computer Science, Technische Universität Dortmund, Otto-Hahn-Strasse 16, 44227, Dortmund, Germany

    Gernot A. Fink

Authors
  1. Thomas Plötz
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Gernot A. Fink
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Thomas Plötz .

Rights and permissions

Reprints and permissions

Copyright information

© 2011 Thomas Plötz

About this chapter

Cite this chapter

Plötz, T., Fink, G.A. (2011). Introduction. In: Markov Models for Handwriting Recognition. SpringerBriefs in Computer Science. Springer, London. https://doi.org/10.1007/978-1-4471-2188-6_1

Download citation

  • DOI: https://doi.org/10.1007/978-1-4471-2188-6_1

  • Published:

  • Publisher Name: Springer, London

  • Print ISBN: 978-1-4471-2187-9

  • Online ISBN: 978-1-4471-2188-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation