New Approach of Feature Extraction Method Based on the Raw Form and his Skeleton for Gujarati Handwritten Digits using Neural Networks Classifier
This paper presents an optical character recognition (OCR) system for Gujarati handwritten digits. One may find so much of work for latin writing, arabic, chines, etc. but Gujarati is a language for which hardly any work is traceable especially for handwritten characters. Here in this work we have p...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Universitatea Dunarea de Jos
2014-12-01
|
Series: | Analele Universităţii "Dunărea de Jos" Galaţi: Fascicula III, Electrotehnică, Electronică, Automatică, Informatică |
Subjects: | |
Online Access: | http://www.ann.ugal.ro/eeai/archives/2014/1%20NEW%20APPROACH%20OF%20FEATURE%20EXTRACTION%20METHOD.pdf |
id |
doaj-a6b7c8b9eea44ffe8c04188f5c2b98ec |
---|---|
record_format |
Article |
spelling |
doaj-a6b7c8b9eea44ffe8c04188f5c2b98ec2020-11-24T22:28:54ZengUniversitatea Dunarea de JosAnalele Universităţii "Dunărea de Jos" Galaţi: Fascicula III, Electrotehnică, Electronică, Automatică, Informatică1221-454X1221-454X2014-12-01371510New Approach of Feature Extraction Method Based on the Raw Form and his Skeleton for Gujarati Handwritten Digits using Neural Networks ClassifierK. Moro0Mohammed Fakir1Belaid Bouikhalene2Rachid El Yachi3Bader Dinne El Kessab4Faculty of Science and Technology Sultan Moulay Slimane University 523, Beni Mellal, MoroccoFaculty of Science and Technology Sultan Moulay Slimane University 523, Beni Mellal, MoroccoFaculty of Science and Technology Sultan Moulay Slimane University 523, Beni Mellal, MoroccoFaculty of Science and Technology Sultan Moulay Slimane University 523, Beni Mellal, MoroccoFaculty of Science and Technology Sultan Moulay Slimane University 523, Beni Mellal, MoroccoThis paper presents an optical character recognition (OCR) system for Gujarati handwritten digits. One may find so much of work for latin writing, arabic, chines, etc. but Gujarati is a language for which hardly any work is traceable especially for handwritten characters. Here in this work we have proposed a method of feature extraction based on the raw form of the character and his skeleton and we have shown the advantage of using this method over other approaches mentioned in this article.http://www.ann.ugal.ro/eeai/archives/2014/1%20NEW%20APPROACH%20OF%20FEATURE%20EXTRACTION%20METHOD.pdfOptical character recognitionneural networkfeature extractionGujarati handwritten digitsskeletonizationclassification |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
K. Moro Mohammed Fakir Belaid Bouikhalene Rachid El Yachi Bader Dinne El Kessab |
spellingShingle |
K. Moro Mohammed Fakir Belaid Bouikhalene Rachid El Yachi Bader Dinne El Kessab New Approach of Feature Extraction Method Based on the Raw Form and his Skeleton for Gujarati Handwritten Digits using Neural Networks Classifier Analele Universităţii "Dunărea de Jos" Galaţi: Fascicula III, Electrotehnică, Electronică, Automatică, Informatică Optical character recognition neural network feature extraction Gujarati handwritten digits skeletonization classification |
author_facet |
K. Moro Mohammed Fakir Belaid Bouikhalene Rachid El Yachi Bader Dinne El Kessab |
author_sort |
K. Moro |
title |
New Approach of Feature Extraction Method Based on the Raw Form and his Skeleton for Gujarati Handwritten Digits using Neural Networks Classifier |
title_short |
New Approach of Feature Extraction Method Based on the Raw Form and his Skeleton for Gujarati Handwritten Digits using Neural Networks Classifier |
title_full |
New Approach of Feature Extraction Method Based on the Raw Form and his Skeleton for Gujarati Handwritten Digits using Neural Networks Classifier |
title_fullStr |
New Approach of Feature Extraction Method Based on the Raw Form and his Skeleton for Gujarati Handwritten Digits using Neural Networks Classifier |
title_full_unstemmed |
New Approach of Feature Extraction Method Based on the Raw Form and his Skeleton for Gujarati Handwritten Digits using Neural Networks Classifier |
title_sort |
new approach of feature extraction method based on the raw form and his skeleton for gujarati handwritten digits using neural networks classifier |
publisher |
Universitatea Dunarea de Jos |
series |
Analele Universităţii "Dunărea de Jos" Galaţi: Fascicula III, Electrotehnică, Electronică, Automatică, Informatică |
issn |
1221-454X 1221-454X |
publishDate |
2014-12-01 |
description |
This paper presents an optical character recognition (OCR) system for Gujarati handwritten digits. One may find so much of work for latin writing, arabic, chines, etc. but Gujarati is a language for which hardly any work is traceable especially for handwritten characters. Here in this work we have proposed a method of feature extraction based on the raw form of the character and his skeleton and we have shown the advantage of using this method over other approaches mentioned in this article. |
topic |
Optical character recognition neural network feature extraction Gujarati handwritten digits skeletonization classification |
url |
http://www.ann.ugal.ro/eeai/archives/2014/1%20NEW%20APPROACH%20OF%20FEATURE%20EXTRACTION%20METHOD.pdf |
work_keys_str_mv |
AT kmoro newapproachoffeatureextractionmethodbasedontherawformandhisskeletonforgujaratihandwrittendigitsusingneuralnetworksclassifier AT mohammedfakir newapproachoffeatureextractionmethodbasedontherawformandhisskeletonforgujaratihandwrittendigitsusingneuralnetworksclassifier AT belaidbouikhalene newapproachoffeatureextractionmethodbasedontherawformandhisskeletonforgujaratihandwrittendigitsusingneuralnetworksclassifier AT rachidelyachi newapproachoffeatureextractionmethodbasedontherawformandhisskeletonforgujaratihandwrittendigitsusingneuralnetworksclassifier AT baderdinneelkessab newapproachoffeatureextractionmethodbasedontherawformandhisskeletonforgujaratihandwrittendigitsusingneuralnetworksclassifier |
_version_ |
1725745783293083648 |