Abstract
This research presents a new work on feature extraction methods for handwritten and isolated Balinese character recognition system. Balinese script has different difficulties compared to other scripts and its uniqueness makes it very interesting yet challenging in the development of this system. The goal of this work is to achieve good performance on Balinese character recognition by comparing more than one feature extractor methods. Based on the experimentations, the direction and semantic features have shown better performance when both are paired as feature extractors. For the classifier, we employed Backpropagation Neural Network with 50 nodes in hidden layer and chosen the Lavenberg-Marquardt as the training algorithm. The overall performance accuracy is 90 %.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sebastiano, I.: More than twenty years of advancements on frontiers in handwriting recognition. Pattern Recogn. 47(3), 916–928 (2014)
Mantas, J.: An overview of character recognition methodologies. Pattern Recogn. 19(6), 425–430 (1986)
Govindan, V.K., et al.: Character recognition—a review. Pattern Recogn. 23(7), 671–683 (1990)
Cheng-Lin, L., Sako, H., Fujisawa, H.: Handwritten chinese character recognition: alternatives to nonlinear normalization. In: ICDAR (2003)
Hariharan, S., et al.: Online handwritten character recognition of devanagari and telugu characters using support vector machines. In: Tenth international workshop on Frontiers in handwriting recognition (2006)
Nawaz, S.N., et al.: An approach to offline arabic character recognition using neural networks. Electronics, circuits and systems, 2003. ICECS 2003. In: Proceedings of the 2003 10th IEEE international conference on. IEEE (2003)
Kawamura, A., et al.: Online recognition of freely handwritten japanese characters using directional feature densities. pattern recognition methodology and systems. In: 11th IAPR international conference on IEEE (1992)
Rudy A., et al., Feature Extraction for Java Character Recognition. Intelligence in the Era of Big Data, pp. 278–288. Springer, Berlin, (2015)
Budhi, G., et al.: Comparison of bidirectional associative memory, counter propagation and evolutionary neural network for java characters recognition. In: Advanced informatics: concept, theory and application (ICAICTA), (2014)
Luh P.A.: Offline balinese handwritten character recognition based on Backpropagation Neural Networks. In: Proceeding of national seminar on computer and intelligent system-KOMMIT 6, pp. 114–118, Bali (2010)
Kadek, A.D.I., Luh P.A.: Character segmentation for balinese script using canny edge detection algorithm. In: Proceedings of national conference of system & informatics, pp. 402–406, Bali (2011)
Luh, P.A.: Noise removal for ancient palm leaf manuscript of Bali. In: Proceedings of National Conference of Information System, KNSI, 1514–1518, Bali (2012)
Trier, Ø., et al.: Feature extraction methods for character recognition-a survey. Pattern Recogn. 29(4), 641–662 (1996)
Zhen-Long B., et al.: A study on the use of 8-directional features for online handwritten chinese character recognition. In: Proceedings eighth international conference on IEEE (2005)
Kato Nei, et al.: A handwritten character recognition system using directional element feature and asymmetric mahalanobis distance. Pattern Anal. Mach. Intell., IEEE Trans. 21(3), 258–262 (1999)
Impedovo, D., Giuseppe, P.: Zoning methods for handwritten character recognition: a survey. Pattern Recogn. 47(3), 969–981 (2013)
Phokharatkul, P., et al.: Off-Line hand written thai character recognition using ant-miner algorithm. Int. J. Comput. Control Quantum Inf. Eng. 1(8), (2007)
Hecht-Nielsen, R.: Theory of the Backpropagation Neural Network. In: IJCNN, International Joint Conference on Neural Networks (1989)
Hagan, M.T., Demuth, H.B., Beale, M.H.: Neural Network Design. Pws Pub, Boston (1996)
Eberhart, R.C. (ed.): Neural Network PC Tools: A Practical Guide. Academic Press (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Science+Business Media Singapore
About this paper
Cite this paper
Prapitasari, L.P.A., Budiarta, K. (2016). Direction and Semantic Features for Handwritten Balinese Character Recognition System. In: Pasila, F., Tanoto, Y., Lim, R., Santoso, M., Pah, N. (eds) Proceedings of Second International Conference on Electrical Systems, Technology and Information 2015 (ICESTI 2015). Lecture Notes in Electrical Engineering, vol 365. Springer, Singapore. https://doi.org/10.1007/978-981-287-988-2_15
Download citation
DOI: https://doi.org/10.1007/978-981-287-988-2_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-287-986-8
Online ISBN: 978-981-287-988-2
eBook Packages: EngineeringEngineering (R0)