Abstract
We present a technique of using Deep Neural Networks (DNNs) for offline character recognition of Telugu characters. We construct DNNs by stacking Auto-encoders that are trained in a greedy layer-wise fashion in an unsupervised manner. We then perform supervised fine-tuning to train the entire network. We provide results on Consonant and Vowel Modifier Datasets using two and three hidden layer DNNs. We also construct an ensemble classifier to increase the classification performance further. We observe 94.25% accuracy for the two hidden layer network on Consonant data and 94.1% on Vowel Modifier Dataset which increases to 95.4% for Consonant and 94.8% for Vowel Modifier Dataset after combining classifiers to form an ensemble classifier of 4 different two hidden layer networks.
This is a preview of subscription content, log in via an institution to check access.
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
Banashree, N., Andhre, D., Vasanta, R.: OCR for script identification of Hindi (Devnagari) numerals using error diffusion Halftoning. In: Proceedings of World Algorithm with Neural Classifier, pp. 46–50 (2007)
Bengio, Y., Lamblin, P., Popovici, D.: Greedy layer-wise training of deep networks. In: Advances in Neural Information Processing Systems (2007)
Erhan, D., Bengio, Y., Courville, A.: Why does unsupervised pre-training help deep learning? Journal of Machine Learning 11, 625–660 (2010)
Guo, X., Yin, Y., Dong, C., Yang, G.: On the class imbalance problem. In: Fourth International Conference on Natural Computation, pp. 192–201 (2008)
Hinton, G.E., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets. Neural Computation 18(7), 1527–1554 (2008)
Ng, A.: Ufldl Tutorial on Neural Networks. Ufldl Tutorial on Neural Networks (2011) retrieved from, http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial
Pal, U., Chaudhuri, B.B.: Indian script character recognition: a survey. Pattern Recognition 37(9), 1887–1899 (2004)
Pal, U., Jayadevan, R., Sharma, N.: Handwriting Recognition in Indian Regional Scripts. ACM Transactions on Asian Language Information Processing 11(1), 1–35 (2012)
Rajashekararadhya, S.V., Vanaja Ranjan, P.: Neural network based handwritten numeral recognition of Kannada and Telugu scripts. In: IEEE Region 10 Conference, pp. 1–5 (2008)
Schmidt, M.: minFunc., http://www.di.ens.fr/~mschmidt/Software/minFunc.html
Vincent, P.: Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion. Journal of Machine Learning Research 11(5), 3371–3408 (2010), doi:10.1111/1467-8535.00290
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dewan, S., Chakravarthy, S. (2012). A System for Offline Character Recognition Using Auto-encoder Networks. In: Huang, T., Zeng, Z., Li, C., Leung, C.S. (eds) Neural Information Processing. ICONIP 2012. Lecture Notes in Computer Science, vol 7666. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34478-7_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-34478-7_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34477-0
Online ISBN: 978-3-642-34478-7
eBook Packages: Computer ScienceComputer Science (R0)