Advertisement

Isan Dhamma Characters Segmentation and Reading in Thai

  • Siriya PhattarachairaweeEmail author
  • Montean Rattanasiriwongwut
  • Mahasak Ketcham
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 807)

Abstract

This paper presents Isan Dhamma Characters Segmentation and Reading in Thai, Palm leaf manuscript is considered as a kind of cultural heritage and the record of local wisdom of ancestors that should be transformed into digital format for educational and research benefits of the next generation. This research presents palm leaf manuscript’s Isan Dhamma characters segmentation and reading conducted by using image processing. The objective of this research is to utilize the obtained data in sentence recognition process further. The input was digital photos of a palm leaf manuscript written with Isan Dhamma characters that was proposed to be adjusted on its quality by adjusting light intensity through histogram. Subsequently, its quality was improved by using median filter in order to screen data on enhancement or attenuation of some picture’s properties in order to gain quality as demanded. Subsequently, characters were segmented from background (segmentation) by using Global Thresholding. In the last process, each character was recognized by using the principles of neural network and compared with support vector machine. After conducting the experiment with 10 images of palm leaf manuscript, it was found that neural network gives better effects than support vector machine by 98%.

Keywords

K-NN Threshold Morphology CM calculation 

References

  1. 1.
    AbdelRaouf, A., Higgins, C.A., Pridmore, T., Khalil, M.: Building a multi-modal Arabic corpus (MMAC). Int. J. Doc. Anal. Recognit. (IJDAR) 13(4), 285–302 (2010)CrossRefGoogle Scholar
  2. 2.
    Oujaoura, M., El Ayachi, R., Fakir, M., Bouikhalene, B., Minaoui, B.: Zernike moments and neural networks for recognition of isolated Arabic characters. Int. J. Comput. Eng. Sci. (IJCES) 2(3), 17–25 (2012)Google Scholar
  3. 3.
    Abulnaja, O., Batawi, Y.: Improving Arabic optical character recognition accuracy using N-version programming technique. Can. J. Image Process. Comput. Vis. 3, 44–46 (2012)Google Scholar
  4. 4.
    Moussa, S.B., Zahour, A., Benabdelhafid, A., Alimi, A.M.: New features using fractal multi-dimensions for generalized Arabic font recognition. Pattern Recognit. Lett. 31(5), 361–371 (2010)CrossRefGoogle Scholar
  5. 5.
    Patel, C.I., Patel, R., Patel, P.: Handwritten character recognition using neural network. Int. J. Sci. Eng. Res. 2(5), 1–6 (2011)Google Scholar
  6. 6.
    Patel, D.K., Som, T., Yadav, S.K., Singh, M.K.: Handwritten character recognition using multiresolution technique and euclidean distance metric (2012)Google Scholar
  7. 7.
    Sahu, V.L., Kubde, B.: Offline handwritten character recognition techniques using neural network: A review. Int. J. Sci. Res. (IJSR) 2(1), 87–94 (2013)Google Scholar
  8. 8.
    Abed, M.A., Alasadi, H.A.A.: Simplifying handwritten characters recognition using a particle swarm optimization approach. Eur. Acad. Res. 1 (2013)Google Scholar
  9. 9.
    Mohammed, J.R.: An improved median filter based on efficient noise detection for high quality image restoration. In: Second Asia International Conference on Modeling and Simulation, AICMS 2008, pp. 327–331. IEEE Press (2007)Google Scholar
  10. 10.
    Pahsa, A.: Morphological image processing with fuzzy logic. J. Aeronaut. Space Technol. 2(3), 27–34 (2006)Google Scholar
  11. 11.
    Wayne, L.W.C.: Mathematical morphology and its applications on image segmentation. Department of Computer Science and Information Engineering, National Taiwan University (2000)Google Scholar
  12. 12.
    Poggio, T., Girosi, F.: Networks for approximation and learning. Proc. IEEE 78(9), 1481–1497 (1990)CrossRefGoogle Scholar
  13. 13.
    Chamchong, R., Fung, C.C.: Text line extraction using adaptive partial projection for palm leaf manuscripts from Thailand. In: 2012 International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 588–593 (2012)Google Scholar
  14. 14.
    Khakham, P., Chumuang, N., Ketcham, M.: Isan Dhamma handwritten characters recognition system by using functional trees classifier. In: 11th International Conference on Signal-Image Technology and Internet Based Systems (SITIS), pp. 606–612 (2015)Google Scholar
  15. 15.
    Chumuang, N., Khakham, P., Ketcham, M.: The intelligence algorithm for character recognition on palm leaf manuscript. Far East J. Math. Sci. 98(3), 333 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Siriya Phattarachairawee
    • 1
    Email author
  • Montean Rattanasiriwongwut
    • 1
  • Mahasak Ketcham
    • 1
  1. 1.Faculty of Information TechnologyKing Mongkut’s University of Technology North BangkokBangkokThailand

Personalised recommendations