Handwritten Bangla Numeral Recognition using Convolutional Neural Networks

Handwritten Bangla numeral recognition has been studied broadly in the last century. This is a very interest subject among the experimenters because of the progression of various pattern recognition algorithms. In this paper, we compare the results of most widely used machine learning method Like Multi Layer Percepton (MLP) and deep learning method like multilayer Convolutional Neural Network (CNN) to get the accuracy of 99.2% using CNN as compared to 97.97% using MLP on Bangla numeral image database named Halder et al.

[1]  Mahantapas Kundu,et al.  A genetic algorithm based region sampling for selection of local features in handwritten digit recognition application , 2012, Appl. Soft Comput..

[2]  P. Lewis.  Ethnologue : languages of the world , 2009 .

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

[4]  M. M. Hafizur Rahman,et al.  Bangla Handwritten Character Recognition using Convolutional Neural Network , 2015 .

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

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

[7]  Bidyut Baran Chaudhuri,et al.  A system towards Indian postal automation , 2004, Ninth International Workshop on Frontiers in Handwriting Recognition.

[8]  Lambert Schomaker,et al.  A Comparison of Feature and Pixel-Based Methods for Recognizing Handwritten Bangla Digits , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[9]  Bidyut B. Chaudhuri,et al.  Computer recognition of printed Bangla script , 1995 .

[10]  Subhadip Basu,et al.  An MLP based Approach for Recognition of Handwritten 'Bangla' Numerals , 2005, IICAI.

[11]  Kaushik Roy,et al.  Individuality of Bangla numerals , 2012, 2012 12th International Conference on Intelligent Systems Design and Applications (ISDA).

[12]  Khawza I. Ahmed,et al.  Handwritten Bangla digit recognition using Sparse Representation Classifier , 2014, 2014 International Conference on Informatics, Electronics & Vision (ICIEV).

[13]  Ching Y. Suen,et al.  A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters , 2009, Pattern Recognit..