A Region Based Design of Deterministic Finite State Automata for Online Recognition of Teeline Shorthand Language Alphabet

  • Vishwanath C. Burkpalli
  • Shivaprakash
  • B. S. Anami
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 14)


This paper discusses a region based deterministic finite state automata for recognition of isolated online Teeline shorthand alphabet. The strokes are drawn in fixed template of size M × N that is M rows and N columns on a tablet or handheld devices, which are further divided into 13 logical regions using the concept of matrices. Features are extracted from each of these regions and are labeled 1 or 0, based on minimum number of pixels covered in that region and are stored in the feature vector. These feature vectors form input to deterministic finite state automata which recognizes the characters drawn. In order to test 54,600 online handwritten isolated Teeline character samples were used as there is no database of online Teeline characters is available. The characters are written five times by twenty writers. It is observed that average recognition rate is 93.57% for novice writers, 96.73% for familiar writers and 98.84% for expert writers, who practiced writing for a week. The method is simple and does not need segmentation of the strokes. Preprocessing is done at the level of regions and only those regions where the stroke passes.


  1. 1.
    Graves A, Fern S, Liwicki M, Bunke H (2008) Unconstrained online handwriting recognition with recurrent neural networks, 1–8 Google Scholar
  2. 2.
    Clarkson J, Hall S, Osborne C, Parkison U (1991) Teeline gold: the course book. Heinemann EducationalGoogle Scholar
  3. 3.
    Nagabhushan P, Anami BS (2002) A knowledge-based approach for recognition of handwritten Pitman shorthand language strokes. Sadhana 27(12):685–698CrossRefGoogle Scholar
  4. 4.
    Leedham CG, Downton AC (1987) Automatic recognition and transcription of Pitman’s handwritten shorthand—an approach to shortforms. Pattern Recogn 20(3):341–348CrossRefGoogle Scholar
  5. 5.
    Louloudis G, Gatos B, Pratikakis I, Halatsis C (2009) Text line and word segmentation of handwritten documents. Pattern Recogn 42(12):3169–3183CrossRefMATHGoogle Scholar
  6. 6.
    Al-Ghoneim K, Alarifi A (2008) Online arabic character recognition for handheld devices. In: Proceedings of international conference on image processing computer vision and pattern recognition, pp 15–22. ISBN 1-60132-20728-7Google Scholar
  7. 7.
    Parui SK, Guin K, Bhattacharya U Chaudhuri BB (2008) Online handwritten Bangla character recognition using HMM. In: ICPR 2008, 19th international conference on pattern recognition, pp 1–4Google Scholar
  8. 8.
    Frinken V, Fischer A, Bunke H, Foornes A (2011) Co-training for handwritten word recognition. In: 2011 international conference on document analysis and recognition, Sep 2011, pp 314–318Google Scholar
  9. 9.
    EL Makhfi N (2011) Platform of transcription the old arabic manuscripts. Int J Eng Sci Technol 3(6):5358–5365Google Scholar
  10. 10.
    Ghosh D, Dube T, Shivaprasad AP (2010) Script recognition—a review. IEEE Trans Pattern Anal Mach Intell 32(12):2142–2161CrossRefGoogle Scholar
  11. 11.
    Zhou XD, Yu JL, Liu CL, Nagasaki T, Marukawa K (2007) Online handwritten Japanese character string recognition incorporating geometric context. In: Ninth international conference on document analysis and recognition (ICDAR 2007) vol 1, Sep 2007, pp 48–52Google Scholar
  12. 12.
    Nakagawa M, Onuma M (2003) Online handwritten Japanese text recognition free from constrains on line direction and character orientation. In: Proceedings of seventh international conference on document analysis and recognition 2003, vol 1, pp 519–523Google Scholar
  13. 13.
    Kunwar R, Ramakrishnan AG (2011) Online handwriting recognition of tamil script using fractal geometry. In: International conference on document analysis and recognition Sep 2011, pp 1389–1393Google Scholar
  14. 14.
    Al-Ammar M (2011) Online handwriting recognition for the arabic letter set common stages of online arabic handwriting recognition system. Recent Res Commun IT, 42–49Google Scholar
  15. 15.
    Ramakrishnan AG (2013) Global and local features for recognition of online handwritten numerals and tamil characters. In: Proceedings of the 4th international workshop on multilingual OCR 16, 2013Google Scholar
  16. 16.
    R. Proceedings (2005) Title handwritten Chinese character recognition author (s) In: The 8th international conference on document analysis creative commons : attribution 3.0 Hong Kong License A study on the use of 8-directional features for online handwritten Chinese, Proceedings of 2005 eight international conference on document analysis recognition 1520-5263/05, vol 1, pp 262–266, 2005Google Scholar
  17. 17.
    Aparna KH, Subramanian V, Kasirajan M, Prakash GV, Chakravarthy VS, Madhvanath S (2004) Online. In: Ninth international workshop on frontiers in handwriting recognition, pp 438–443Google Scholar
  18. 18.
    Kavallieratou E, Sgarbas K (2003) Handwritten word recognition based on structural characteristics and lexical support. In: Document analysis and recognition 1:562–566Google Scholar
  19. 19.
    Abuzaraida MA, Zeki AM, Zeki AM (2012) Recognition techniques for online arabic handwriting recognition systems. In: International conference on advanced computer science applications and technologies, Nov 2012, pp 518–523Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Vishwanath C. Burkpalli
    • 1
  • Shivaprakash
    • 2
  • B. S. Anami
    • 3
  1. 1.Department of Information Science and EngineeringPDA College of EngineeringGulbargaIndia
  2. 2.Department of Computer Science and EngineeringGovernment Engineering College, DevagiriHaveriIndia
  3. 3.KLE Institute of TechnologyHubliIndia

Personalised recommendations