Abstract
An important problem that decreases the accuracy in Thai Printed Character Recognition system is the errors in segmentation process. In vertical connected character segmentation, we can easily use the reference lines of Thai language structure. This paper thus proposes a method for detecting the connecting points in horizontal connected characters. First, we extract the features of the connecting points in the character images. Then, we employ Inductive Logic Programming to produce the rules that will be used to classify the unseen examples. Finally, we use Backpropagation Neural Network to make these rules more flexible. The results show that our method achieves 94.94% of accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Casey, G., Lecolinet, E.: A Survey of Methods and Strategies in Character Segmentation. IEEE on pattern Analysis and machine intelligence 18 (1996)
Jaiin, A.K.: The Fundamental Digital Image Processing. Prentice-Hall International Editions, pp. 382–383 (1989)
Keittisirianan, J., Kurtachoo, B.: A Segmentation of Thai Printed Characters Using Shortest Path Algorithm. In: Proceedings of 21st EECON 1998, pp. 561–564 (1998)
Kijsirikul, B., Sinthupinyo, S., Chongkasemwongse, K.: Approximate Match of Rules Using Backpropagation Neural Network. Machine Learning 44(3) (2001)
Kongthawornwattana, S., Jitapunkul, S.: Segmentation of Thai-Printed Character String by Modified Freeman Coding of Boundary of Histogram. In: Proceedings of 19th EECON 1996, pp. DS-73–DS-77 (1996)
Muggleton, S.: Inductive Logic Programming. New Generation Computing, 295–318 (1991)
Muggleton, S.: Inverse entailment and PROGOL. New Generation Computing 13, 245–286 (1995)
Premchaiswadi, N., Premchaiswadi, W., Narita, S.: Segmentation of Horizontal and Vertical Touching Thai Characters. IEICE TRANS 2000Â 83-A(6) (2000)
Quinlan, J.R.: C4.5 Programs for machine learning. Morgan Kaufmann, San Mateo (1993)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning Internal Representations by Error Propagation. In: Rumelhart, D.E., McClelland, J.L. (eds.) Parallel distributed processing, vol. 1. MIT Press, Cambridge (1986)
Sinthupinyo, S., Kijsirikul, B.: Approximation of First-Order Rules by the Backpropagation Neural Network. In: The First National Computer Science and Engineering Conference (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pipanmaekaporn, L., Sachdev, A. (2003). Classification of Connecting Points in Thai Printed Characters by combining Inductive Logic Programming with Backpropagation Neural Network. In: Petkov, N., Westenberg, M.A. (eds) Computer Analysis of Images and Patterns. CAIP 2003. Lecture Notes in Computer Science, vol 2756. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45179-2_69
Download citation
DOI: https://doi.org/10.1007/978-3-540-45179-2_69
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40730-0
Online ISBN: 978-3-540-45179-2
eBook Packages: Springer Book Archive