Applied Finite Automata and Quadtree Technique for Thai Sign Language Translation

Conference paper


In this article, algorithm for transforming sign language into Thai alphabets is presented to fill the gap in communication between the hearing impairment and normal people. Leap Motion Controller was applied to detect 5-finger-tip position and palm center in the form of X and Y axis. Then, decision tree was created by using the Quadtree technique and the research result on transforming Thai sign language into finite automata was applied to improve algorithm in creating finite automata of Thai alphabet sign language to increase efficiency and speed in processing sign language. The test result shows that it can discriminate 42-Thai alphabet sign language at 78.70% accuracy.


Communication Finite automata Hearing impairment people Leap motion controller Quadtree Thai sign language 


  1. 1.
    J. Bunyarattanasuntorn, Quality of Life of the Deft: Reflection of Monitoring and Evaluation of the 4th National Development Plan for Quality of Life of The Hearing Impairment People, 2015–2016, in Proceeding Articles in 7th National Academic Conference on the Deft People, vol. 2 (2015), pp. 33–58Google Scholar
  2. 2.
    Thai Telecommunication Relay Service. TTRS Machine for the hearing impairment people: Reduction of communication gap, Accessed 22 Nov 2016
  3. 3.
    M. Thammasaeng, “Sign Language,” Bangkok: Jong Chareon Printing, Sign Language, vol. 2 (1996)Google Scholar
  4. 4.
    W. Tangwongcharoen, J. Tumsri, Decoding thai sign language pattern using quad tree, in Proceedings of the 37th Electrical Engineering Conference (EECON37), Khon Kaen, Thailand, vol. 2, pp. 873–876, 19–3 Nov 2014Google Scholar
  5. 5.
    Ajangz. 2015. Quadtree, Accessed 10 Nov 2016
  6. 6.
    K. Jiaranaithanakit, Theory of Computation, 2nd edn. (Bangkok: Technology Promotion Association, Thailand-Japan, 2014), ch. 2, pp. 20–23Google Scholar
  7. 7.
    P. Linz, An Introduction to formal languages and Automata, 4th edn. (London, UK: Jones and Bartlett Publishers, 2006), ch. 1, pp. 26–28Google Scholar
  8. 8.
    Q. Munib, M. Habeeb, B. Takruri, H.A. Al-Malik, American sign language (ASL) recognition based on Hough transform and neural networks. Sci. Direct Expert Syst. Appl. 32, 24–27 (2007)CrossRefGoogle Scholar
  9. 9.
    S. Phitakwinai, S. Auephanwiriyakul, N. Theera-Umpon, Thai sign language translation using fuzzy c-means and scale invariant feature transform, in ICCSA 2008, pp. 1107–1119, 30 Jun.-3 Jul. 2008Google Scholar
  10. 10.
    J. Tumsri, W. Kimpan, Code translation from Thai sign language pattern to finite automata, in Proceedings of the 7th Conference of Electrical Engineering Network of Rajamangala University of Technology 2015 (EENET 2015), A-one The Royal Cruise Hotel, Pattaya, Chonburi, Thailand, pp. 125–128, 27–29 May 2015Google Scholar
  11. 11.
    M.M. Deza, E. Deza, Encyclopedia of Distances (Springer Science & Business Media, 2009), p. 94Google Scholar
  12. 12.
    J. Tumsri, W. Kimpan, Thai sign language translation using leap motion controller, in Proceedings of The International MultiConference of Engineers and Computer Scientists 2017. Lecture Notes in Engineering and Computer Science, 15–17 Mar 2017, Hong Kong, pp. 46–51Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Department of Computer Science, Faculty of ScienceKing Mongkut’s Institute of Technology Ladkrabang (KMITL)BangkokThailand

Personalised recommendations