A system for offline character recognition using auto-encoder networks

Authors:
Sagar Dewan;Srinivasa Chakravarthy
Affiliations:
Department of Electrical Engineering, Indian Institute of Technology, Madras, Chennai, India;Department of Biotechnology, Indian Institute of Technology, Madras, Chennai, India
Venue:
ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part IV
Year:
2012

Citing 5
Cited 0

A fast learning algorithm for deep belief nets

Neural Computation
On the Class Imbalance Problem

ICNC '08 Proceedings of the 2008 Fourth International Conference on Natural Computation - Volume 04
Why Does Unsupervised Pre-training Help Deep Learning?

The Journal of Machine Learning Research
Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion

The Journal of Machine Learning Research
Handwriting Recognition in Indian Regional Scripts: A Survey of Offline Techniques

ACM Transactions on Asian Language Information Processing (TALIP)

Quantified Score

Hi-index	0.00

Visualization

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.