A neural network-based approach for recognizing multi-font printed English characters

In this paper, we propose a method for recognizing English characters in different fonts. The proposed method based on neural network is resistant to font variant. When the samples in new fonts are added to the database, the accuracy of existing methods rapidly decreases and they are not resistant t...

Full description

Bibliographic Details
Main Authors: Najmeh Samadiani, Hamid Hassanpour
Format: Article
Language:English
Published: SpringerOpen 2015-09-01
Series:Journal of Electrical Systems and Information Technology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2314717215000355
id doaj-a32d60ea30bb452ea843a3b37a68bc20
record_format Article
spelling doaj-a32d60ea30bb452ea843a3b37a68bc202020-11-25T01:17:59ZengSpringerOpenJournal of Electrical Systems and Information Technology2314-71722015-09-012220721810.1016/j.jesit.2015.06.003A neural network-based approach for recognizing multi-font printed English charactersNajmeh SamadianiHamid HassanpourIn this paper, we propose a method for recognizing English characters in different fonts. The proposed method based on neural network is resistant to font variant. When the samples in new fonts are added to the database, the accuracy of existing methods rapidly decreases and they are not resistant to font variant but to the accuracy of proposed method that almost stays constant and does not much decrease. A similarity measure neural network is used to identify characters and similarity measure compares the features of characters and the features of the indicators associated with the characters from A to Z obtained in the training stage. We use similarity measure instead of distance measure in SOM neural network because a person learns font-independent and a literate can read without knowing the font of the written note. In fact he/she measures similarity between the notes in new fonts and learned notes in his/her mind. Therefore, we use two samples for training the network as representative of all fonts such as default notes in man's mind. We could obtain 98.56% accuracy of recognizing a database that includes 24 different fonts in 11 different sizes.http://www.sciencedirect.com/science/article/pii/S2314717215000355Character recognitionSimilarity measureFeature extractionSOM neural network
collection DOAJ
language English
format Article
sources DOAJ
author Najmeh Samadiani
Hamid Hassanpour
spellingShingle Najmeh Samadiani
Hamid Hassanpour
A neural network-based approach for recognizing multi-font printed English characters
Journal of Electrical Systems and Information Technology
Character recognition
Similarity measure
Feature extraction
SOM neural network
author_facet Najmeh Samadiani
Hamid Hassanpour
author_sort Najmeh Samadiani
title A neural network-based approach for recognizing multi-font printed English characters
title_short A neural network-based approach for recognizing multi-font printed English characters
title_full A neural network-based approach for recognizing multi-font printed English characters
title_fullStr A neural network-based approach for recognizing multi-font printed English characters
title_full_unstemmed A neural network-based approach for recognizing multi-font printed English characters
title_sort neural network-based approach for recognizing multi-font printed english characters
publisher SpringerOpen
series Journal of Electrical Systems and Information Technology
issn 2314-7172
publishDate 2015-09-01
description In this paper, we propose a method for recognizing English characters in different fonts. The proposed method based on neural network is resistant to font variant. When the samples in new fonts are added to the database, the accuracy of existing methods rapidly decreases and they are not resistant to font variant but to the accuracy of proposed method that almost stays constant and does not much decrease. A similarity measure neural network is used to identify characters and similarity measure compares the features of characters and the features of the indicators associated with the characters from A to Z obtained in the training stage. We use similarity measure instead of distance measure in SOM neural network because a person learns font-independent and a literate can read without knowing the font of the written note. In fact he/she measures similarity between the notes in new fonts and learned notes in his/her mind. Therefore, we use two samples for training the network as representative of all fonts such as default notes in man's mind. We could obtain 98.56% accuracy of recognizing a database that includes 24 different fonts in 11 different sizes.
topic Character recognition
Similarity measure
Feature extraction
SOM neural network
url http://www.sciencedirect.com/science/article/pii/S2314717215000355
work_keys_str_mv AT najmehsamadiani aneuralnetworkbasedapproachforrecognizingmultifontprintedenglishcharacters
AT hamidhassanpour aneuralnetworkbasedapproachforrecognizingmultifontprintedenglishcharacters
AT najmehsamadiani neuralnetworkbasedapproachforrecognizingmultifontprintedenglishcharacters
AT hamidhassanpour neuralnetworkbasedapproachforrecognizingmultifontprintedenglishcharacters
_version_ 1725144454095962112