Convolutional neural network based handwritten Bengali and Bengali-English mixed numeral recognition

Recognition of handwritten numerals has gained much interest in recent years due to its various potential applications. Bengali is the fifth ranked among the spoken languages of the world. However, due to inherent difficulties of Bengali numeral recognition, a very few study on handwritten Bengali n...

Full description

Bibliographic Details
Main Authors: Akhand, M. A. H, Ahmed, Mahtab, Rahman, M.M. Hafizur
Format: Article
Language:English
Published: Modern Education and Computer Science Press 2016
Subjects:
Online Access:http://irep.iium.edu.my/52028/
http://irep.iium.edu.my/52028/1/IJIGSP-V8-N9-6.pdf
_version_ 1848783980938133504
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
building IIUM Repository
collection Online Access
description Recognition of handwritten numerals has gained much interest in recent years due to its various potential applications. Bengali is the fifth ranked among the spoken languages of the world. However, due to inherent difficulties of Bengali numeral recognition, a very few study on handwritten Bengali numeral recognition is found with respect to other major languages. The existing Bengali numeral recognition methods used distinct feature extraction techniques and various classification tools. Recently, convolutional neural network (CNN) is found efficient for image classification with its distinct features. In this paper, we have investigated a CNN based Bengali handwritten numeral recognition scheme. Since English numerals are frequently used with Bengali numerals, handwritten Bengali-English mixed numerals are also investigated in this study. The proposed scheme uses moderate pre-processing technique to generate patterns from images of handwritten numerals and then employs CNN to classify individual numerals. It does not employ any feature extraction method like other related works. The proposed method showed satisfactory recognition accuracy on the benchmark data set and outperformed other prominent existing methods for both Bengali and Bengali-English mixed cases.
first_indexed 2025-11-14T16:29:59Z
format Article
id iium-52028
institution International Islamic University Malaysia
institution_category Local University
language English
last_indexed 2025-11-14T16:29:59Z
publishDate 2016
publisher Modern Education and Computer Science Press
recordtype eprints
repository_type Digital Repository
spelling iium-520282016-09-30T01:52:08Z http://irep.iium.edu.my/52028/ Convolutional neural network based handwritten Bengali and Bengali-English mixed numeral recognition Akhand, M. A. H Ahmed, Mahtab Rahman, M.M. Hafizur TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices TK7885 Computer engineering Recognition of handwritten numerals has gained much interest in recent years due to its various potential applications. Bengali is the fifth ranked among the spoken languages of the world. However, due to inherent difficulties of Bengali numeral recognition, a very few study on handwritten Bengali numeral recognition is found with respect to other major languages. The existing Bengali numeral recognition methods used distinct feature extraction techniques and various classification tools. Recently, convolutional neural network (CNN) is found efficient for image classification with its distinct features. In this paper, we have investigated a CNN based Bengali handwritten numeral recognition scheme. Since English numerals are frequently used with Bengali numerals, handwritten Bengali-English mixed numerals are also investigated in this study. The proposed scheme uses moderate pre-processing technique to generate patterns from images of handwritten numerals and then employs CNN to classify individual numerals. It does not employ any feature extraction method like other related works. The proposed method showed satisfactory recognition accuracy on the benchmark data set and outperformed other prominent existing methods for both Bengali and Bengali-English mixed cases. Modern Education and Computer Science Press 2016-09 Article PeerReviewed application/pdf en http://irep.iium.edu.my/52028/1/IJIGSP-V8-N9-6.pdf Akhand, M. A. H and Ahmed, Mahtab and Rahman, M.M. Hafizur (2016) Convolutional neural network based handwritten Bengali and Bengali-English mixed numeral recognition. International Journal of Image, Graphics and Signal Processing (IJIGSP), 8 (9). pp. 40-50. ISSN 2074-9074 E-ISSN 2074-9082 http://www.mecs-press.org/ijigsp/ijigsp-v8-n9/IJIGSP-V8-N9-6.pdf 10.5815/ijigsp.2016.09.06
spellingShingle TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices
TK7885 Computer engineering
Akhand, M. A. H
Ahmed, Mahtab
Rahman, M.M. Hafizur
Convolutional neural network based handwritten Bengali and Bengali-English mixed numeral recognition
title Convolutional neural network based handwritten Bengali and Bengali-English mixed numeral recognition
title_full Convolutional neural network based handwritten Bengali and Bengali-English mixed numeral recognition
title_fullStr Convolutional neural network based handwritten Bengali and Bengali-English mixed numeral recognition
title_full_unstemmed Convolutional neural network based handwritten Bengali and Bengali-English mixed numeral recognition
title_short Convolutional neural network based handwritten Bengali and Bengali-English mixed numeral recognition
title_sort convolutional neural network based handwritten bengali and bengali-english mixed numeral recognition
topic TK7800 Electronics. Computer engineering. Computer hardware. Photoelectronic devices
TK7885 Computer engineering
url http://irep.iium.edu.my/52028/
http://irep.iium.edu.my/52028/
http://irep.iium.edu.my/52028/
http://irep.iium.edu.my/52028/1/IJIGSP-V8-N9-6.pdf