Lanna Handwritten Character Recognition on Historical Documents Using Feature Extraction

Abstract:

The objective of this paper is to develop methodology that can recognize the Lanna handwritten character on historical documents by using character feature extraction technique. Historical documents are national treasures. Insignificant effort has been made to preserve Lanna historical documents. Other nations such as Egypt, China and Greece are investing a large effort in restoring and preserving their national historical documents. As a starting point, the focus is on using one Lanna historical document for performing experiments and verifying recognition methods available in this research area. The proposed system consists of three modules, which are image preprocessing module, feature extraction module and character recognition module. The details of each module are following: first, the input image is transformed into a suitable image for feature extraction module. Second, the proposed system extracts character features from the image. Finally, the extracted character information, which is kept in form of bit string, is calculated a similarity value for recognition result. The experiment was conducted on more than 4,000 Lanna handwritten characters by using 10-fold cross-validation classification method which is using 3,600 for training characters and 400 for testing character. The cross-validation process is repeated 10 times, with each of the 10 subsets used exactly once as the validation data. The precision of the proposed system is around 89.73 percent.

• Periodical: Applied Mechanics and Materials (Volumes 263-266)
• Pages: 2553-2560
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.263-266.2553
• Online since: December 2012
• Authors: Krisda Khankasikam*
• Keywords: Character Feature Extraction, Handwritten Recognition, Lanna Historical Document

References

[1] K. Khankasikam: Printed Lanna character recognition by using Conway's game of life. Proc. 7th Int. Conf. Digital Information Management (2012), pp.104-109.

DOI: 10.1109/icdim.2012.6360138

[2] C. Pornpanomchai, D. N. Batanov and N. Dimmitt: Recognizing Thai handwritten characters and words for human-computer interaction. Int. Jour. Human-Computer Studies (2001), pp.259-279.

DOI: 10.1006/ijhc.2001.0466

[3] C. Pornpanomchai, P. Panyasrivarom, N. Pisitviroj and P. Prutkraiwat: Thai handwritten character recognition by euclidean distance. Proc. 2nd Int. Conf. Digital Image Processing (2010), pp.53-58.

DOI: 10.1117/12.852245

[4] C. Pornpanomchai and M. Daveloh: Printed Thai character recognition by genetic algorithm. Proc. Int. Conf. Machine Learning and Cybernetics (2007), pp.3354-3359.

DOI: 10.1109/icmlc.2007.4370727

[5] B. Kruatrachue, N. Pantrakarn and K. Siriboon: State machine induction with positive and negative for Thai character recognition. Proc. Int. Conf. Communications, Circuits and Systems (2007), pp.971-975.

DOI: 10.1109/icccas.2007.4348209

[6] P. Sanguansat, W. Asdornwised and S. Jitapunkul: Online Thai handwritten character recognition using hidden Markov models and Support Vector Machines. Proc. Int. Symp. Communications and Information Technologies (2004), pp.492-497.

DOI: 10.1109/iscit.2004.1412894

[7] R. Budsayaplakorn, W. Asdornwised and S. Jitapunkul: On-line Thai handwritten character recognition using hidden Markov model and fuzzy logic. Proc. 13th IEEE Workshop on Neural Networks for Signal Processing (2003), pp.537-546.

DOI: 10.1109/nnsp.2003.1318053

[8] K. Siriboon, A. Jirayusakul and B. Kruatrachue: HMM topology selection for on-line Thai handwriting recognition. Proc. 1st Int. Symp. Cyber Worlds (2002), pp.142-145.

DOI: 10.1109/cw.2002.1180872

[9] A. Pornchaikajornsak and A. Thammano: Handwritten Thai character recognition using fuzzy membership function and fuzzy ARTMAP. Proc. IEEE Int. Symp. Computational Intelligence in Robotics and Automation (2003), pp.40-44.

DOI: 10.1109/cira.2003.1222060

[10] S. Tangwongsan and O. Jungthanawong: Refinement of stroke structure for printed Thai character recognition. Proc. 9th Int. Conf. Signal Processing (2008), pp.1504-1507.

DOI: 10.1109/icosp.2008.4697418

[11] K. Bounnady, B. Kruatrachue and T. Matsuura: Online unconstrained handwritten Thai character recognition using multiple representations. Proc. Int. Symp. Communications and Information Technologies (2008), pp.135-140.

DOI: 10.1109/iscit.2008.4700169

[12] J. L. Mitrpanont and U. Limkonglap: Using contour analysis to improve feature extraction in Thai handwritten character recognition systems. Proc. 7th IEEE Int. Conf. Computer and Information Technology (2007), pp.668-673.

DOI: 10.1109/cit.2007.103

[13] I. Methasate, S. Marukatat, S. Sae-tang and T. Theeramunkong: The feature combination technique for off-line Thai character recognition system. Proc. 8th Int. Conf. Document Analysis and Recognition (2005), pp.1006-1009.

DOI: 10.1109/icdar.2005.236

[14] T. Thongkamwitoon, W. Asdornwised, S. Aramvith and S. Jitapunkul: On-line Thai-English handwritten character recognition using distinctive features. Proc. Asia-Pacific Conf. Circuits and Systems (2002), pp.259-264.

DOI: 10.1109/apccas.2002.1115220

[15] A. Thammano and P. Duangphasuk: Printed Thai character recognition using the hierarchical cross-correlation ARTMAP. Proc. 17th IEEE Int. Conf. Tools with Artificial Intelligence (2005), pp.695-698.

DOI: 10.1109/ictai.2005.100

[16] W. Chatwiriya, P. Klinkhachorn and N. Lass: Thai handwriting legal amounts recognition. Proc. 35th Southeastern Symp. System Theory (2003), pp.381-385.

DOI: 10.1109/ssst.2003.1194596

[17] A. Thammano and P. Poolsamran: Applying a weighting matrix to the hierarchical neural network model for handwritten Thai character recognition. Proc. Int. Conf. Computational Intelligence for Modelling, Control and Automation, and Int. Conf. Intelligent Agents, Web Technologies and Internet Commerce (2006), pp.85-89.

DOI: 10.1109/cimca.2006.50