Open Access Open Access  Restricted Access Subscription or Fee Access

Application of Deep-Learning Neural Network for the recognition of Devanagari characters

Pratibha Singh, Ajay Verma, Narendra S. Chaudhari

Abstract



This paper aims to provide an experimental framework for the recognition of Devanagari characters/numerals using various deep-learning tools. The main advantage of deep learning is that it makes maximal use of unsupervised learning. The implemented architectures are based on Neural network. The method makes use of deep learning algorithms inspired from human vision system. The method requires little or no preprocessing and uses the direct pixel intensities as feature rather than especially designed/crafted features. The performance is comparable or sometimes better than previously reported results on the dataset of Devanagari character/numerals.

Keywords


Multilayer Perceptron(MLP), Neural Network(NN), Stacked Denoising Autoencoder(SDAE), Deep Belief Network(DBN), Convolutional Neural Network(CNN).

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information. Also: DOI is paid service which provided by a third party. We never mentioned that we go for this for our any journal. However, journal have no objection if author go directly for this paid DOI service.