Multiple convolutional neural network training for Bangla handwritten numeral recognition

Recognition of handwritten numerals has gained much interest in recent years due to its various application potentials. The progress of handwritten Bangla numeral is well behind Roman, Chinese and Arabic scripts although it is a major language in Indian subcontinent and is the first language of Bang...

Full description

Bibliographic Details
Main Authors:	Akhand, M. A. H, Ahmed, Mahtab, Rahman, M.M. Hafizur
Format:	Conference or Workshop Item
Language:	English English English
Published:	Institute of Electrical and Electronics Engineers Inc. 2016
Subjects:	TK Electrical engineering. Electronics Nuclear engineering
Online Access:	http://irep.iium.edu.my/51419/ http://irep.iium.edu.my/51419/ http://irep.iium.edu.my/51419/ http://irep.iium.edu.my/51419/1/51419_Multiple_convolutional_neural_network.pdf http://irep.iium.edu.my/51419/4/51419_Multiple%20convolutional%20neural%20network%20training_SCOPUS.pdf http://irep.iium.edu.my/51419/10/51419_Multiple%20Convolutional%20Neural%20Network_WOS.pdf

id	iium-51419
recordtype	eprints
spelling	iium-514192019-06-26T06:59:38Z http://irep.iium.edu.my/51419/ Multiple convolutional neural network training for Bangla handwritten numeral recognition Akhand, M. A. H Ahmed, Mahtab Rahman, M.M. Hafizur TK Electrical engineering. Electronics Nuclear engineering Recognition of handwritten numerals has gained much interest in recent years due to its various application potentials. The progress of handwritten Bangla numeral is well behind Roman, Chinese and Arabic scripts although it is a major language in Indian subcontinent and is the first language of Bangladesh. Handwritten numeral classification is a high-dimensional complex task and existing methods use distinct feature extraction techniques and various classification tools in their recognition schemes. Recently, convolutional neural network (CNN) is found efficient for image classification with its distinct features. In this study, three different CNNs with same architecture are trained with different training sets and combined their decisions for Bangla handwritten numeral recognition. One CNN is trained with ordinary training set prepared from handwritten scan images; and training sets for other two CNNs are prepared with fixed (positive and negative, respectively) rotational angles of original images. The proposed multiple CNN based approach is shown to outperform other existing methods while tested on a popular Bangla benchmark handwritten dataset. Institute of Electrical and Electronics Engineers Inc. 2016-07-26 Conference or Workshop Item PeerReviewed application/pdf en http://irep.iium.edu.my/51419/1/51419_Multiple_convolutional_neural_network.pdf application/pdf en http://irep.iium.edu.my/51419/4/51419_Multiple%20convolutional%20neural%20network%20training_SCOPUS.pdf application/pdf en http://irep.iium.edu.my/51419/10/51419_Multiple%20Convolutional%20Neural%20Network_WOS.pdf Akhand, M. A. H and Ahmed, Mahtab and Rahman, M.M. Hafizur (2016) Multiple convolutional neural network training for Bangla handwritten numeral recognition. In: 6th International Conference on Computer and Communication Engineering (ICCCE 2016), 25th-27th July 2016, Kuala Lumpur. https://ieeexplore.ieee.org/document/7808331 10.1109/ICCCE.2016.102
repository_type	Digital Repository
institution_category	Local University
institution	International Islamic University Malaysia
building	IIUM Repository
collection	Online Access
language	English English English
topic	TK Electrical engineering. Electronics Nuclear engineering
spellingShingle	TK Electrical engineering. Electronics Nuclear engineering Akhand, M. A. H Ahmed, Mahtab Rahman, M.M. Hafizur Multiple convolutional neural network training for Bangla handwritten numeral recognition
description	Recognition of handwritten numerals has gained much interest in recent years due to its various application potentials. The progress of handwritten Bangla numeral is well behind Roman, Chinese and Arabic scripts although it is a major language in Indian subcontinent and is the first language of Bangladesh. Handwritten numeral classification is a high-dimensional complex task and existing methods use distinct feature extraction techniques and various classification tools in their recognition schemes. Recently, convolutional neural network (CNN) is found efficient for image classification with its distinct features. In this study, three different CNNs with same architecture are trained with different training sets and combined their decisions for Bangla handwritten numeral recognition. One CNN is trained with ordinary training set prepared from handwritten scan images; and training sets for other two CNNs are prepared with fixed (positive and negative, respectively) rotational angles of original images. The proposed multiple CNN based approach is shown to outperform other existing methods while tested on a popular Bangla benchmark handwritten dataset.
format	Conference or Workshop Item
author	Akhand, M. A. H Ahmed, Mahtab Rahman, M.M. Hafizur
author_facet	Akhand, M. A. H Ahmed, Mahtab Rahman, M.M. Hafizur
author_sort	Akhand, M. A. H
title	Multiple convolutional neural network training for Bangla handwritten numeral recognition
title_short	Multiple convolutional neural network training for Bangla handwritten numeral recognition
title_full	Multiple convolutional neural network training for Bangla handwritten numeral recognition
title_fullStr	Multiple convolutional neural network training for Bangla handwritten numeral recognition
title_full_unstemmed	Multiple convolutional neural network training for Bangla handwritten numeral recognition
title_sort	multiple convolutional neural network training for bangla handwritten numeral recognition
publisher	Institute of Electrical and Electronics Engineers Inc.
publishDate	2016
url	http://irep.iium.edu.my/51419/ http://irep.iium.edu.my/51419/ http://irep.iium.edu.my/51419/ http://irep.iium.edu.my/51419/1/51419_Multiple_convolutional_neural_network.pdf http://irep.iium.edu.my/51419/4/51419_Multiple%20convolutional%20neural%20network%20training_SCOPUS.pdf http://irep.iium.edu.my/51419/10/51419_Multiple%20Convolutional%20Neural%20Network_WOS.pdf
first_indexed	2023-09-18T21:12:48Z
last_indexed	2023-09-18T21:12:48Z
_version_	1777411364725194752

Multiple convolutional neural network training for Bangla handwritten numeral recognition

Similar Items