Abstract
We come across a large volume of handwritten texts in our daily lives and handwritten character recognition has long been an important area of research in pattern recognition. The complexity of the task varies among different languages and it so happens largely due to the similarity between characters, distinct shapes and number of characters which are all language-specific properties. There have been numerous works on character recognition of English alphabets and with laudable success, but regional languages have not been dealt with very frequently and with similar accuracies. In this paper, we explored the performance of Convolutional Neural Networks, and Deep Belief Networks in the classification of Handwritten Kannada numerals, and conclusively compared the results obtained. The proposed method has shown satisfactory recognition accuracy in light of difficulties faced with regional languages such as similarity between characters and minute nuances that differentiate them. We can further extend this to all the Kannada characters.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet Classification with Deep Convolutional Neural Networks (2012)
Bengio Y., Glorot X.: Understanding the difficulty of training deep forward neural networks. In: AISTATS (2010)
Bengio, Y., Lambli, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Advances in Neural Information Processing Systems 19 (NIPS 2006), pp. 153–160. MIT Press (2007)
Bishop, C.M.: Neural Networks for Pattern Recognition, Clarendon (1995)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Hubel, D., Wiesel, T.: Receptive fields and functional architecture of monkey striate cortex. J. Physiol. (London) 195, 215–243 (1968)
Karthik, S., Srikanta Murthy, K.: Deep belief network based approach to recognize handwritten kannada characters using histogram of oriented gradients and raw pixel features. IJAER (2016)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. In: Proceedings of the IEEE (1998)
LeNet5, Convolutional Neural Networks. http://yann.lecun.com/exdb/lenet/
Keyvanrad, M.A., Homayounpour, M.M.: A brief survey on deep belief networks and introducing a new object oriented toolbox DeeBNet (2014). arXiv:1408.3264
Ritesh, S., Das, N., Amit, K.S., Mita, N.: A multi-objective approach towards cost effective isolated handwritten Bangla character and digit recognition (2016)
Theano’s CUDA bindings: http://bit.ly/2gHY6oE
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Ganesh, A., Jadhav, A.R., Pragadeesh, K.A.C. (2018). Deep Learning Approach for Recognition of Handwritten Kannada Numerals. In: Abraham, A., Cherukuri, A., Madureira, A., Muda, A. (eds) Proceedings of the Eighth International Conference on Soft Computing and Pattern Recognition (SoCPaR 2016). SoCPaR 2016. Advances in Intelligent Systems and Computing, vol 614. Springer, Cham. https://doi.org/10.1007/978-3-319-60618-7_29
Download citation
DOI: https://doi.org/10.1007/978-3-319-60618-7_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-60617-0
Online ISBN: 978-3-319-60618-7
eBook Packages: EngineeringEngineering (R0)