EkushNet: Using Convolutional Neural Network for Bangla Handwritten Recognition

Abstract EkushNet is the first research which can recognize Bangla handwritten basic characters, digits, modifiers, and compound characters. Handwritten recognition is one of the most interesting issue in present time due to its variant applications and help to make the old form and information digitization and reliable. In spite of, there is no single model which can classify all types of Bangla characters. One of most common reason conducting with handwritten scripts is big challenge because of every person has unique style to write and also has different shape and size. Therefore, EkushNet is proposed a model which help to recognize Bangla handwritten 50 basic characters, 10 digits, 10 modifiers and 52 mostly used compound characters. The proposed model train and validate with Ekush [1] dataset and cross-validated with CMATERdb [2] dataset. The proposed method is shown satisfactory recognition accuracy 97.73% for Ekush dataset, and 95.01% cross-validation accuracy on CMATERdb dataset, which is so far, the best accuracy for Bangla character recognition.

[1]  Nikos Fakotakis,et al.  The GRUHD database of Greek unconstrained handwriting , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[2]  Subhadip Basu,et al.  CMATERdb1: a database of unconstrained handwritten Bangla and Bangla–English mixed script document image , 2011, International Journal on Document Analysis and Recognition (IJDAR).

[3]  Masaki Nakagawa,et al.  A robust model for on-line handwritten japanese text recognition , 2009, International Journal on Document Analysis and Recognition (IJDAR).

[4]  Subhadip Basu,et al.  Handwritten Bangla Basic and Compound character recognition using MLP and SVM classifier , 2010, ArXiv.

[5]  Umapada Pal,et al.  Touching numeral segmentation using water reservoir concept , 2003, Pattern Recognit. Lett..

[6]  Mahantapas Kundu,et al.  Handwritten isolated Bangla compound character recognition: A new benchmark using a novel deep learning approach , 2017, Pattern Recognit. Lett..

[7]  Bidyut Baran Chaudhuri,et al.  A complete printed Bangla OCR system , 1998, Pattern Recognit..

[8]  Riasat Azim,et al.  Bangla Hand Written Character Recognition Using Support Vector Machine , 2016 .

[9]  Kunihiko Fukushima,et al.  Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position , 1980, Biological Cybernetics.

[10]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[11]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..