Optical character recognition in real environments using neural networks and k-nearest neighbor
Identifieur interne : 000190 ( Main/Exploration ); précédent : 000189; suivant : 000191Optical character recognition in real environments using neural networks and k-nearest neighbor
Auteurs : O. Matei [Roumanie] ; P. C. Pop [Roumanie] ; H. Valean [Roumanie]Source :
- Applied intelligence : (Boston) [ 0924-669X ] ; 2013.
Descripteurs français
- Pascal (Inist)
English descriptors
- KwdEn :
Abstract
In this paper, we propose a novel process to optical character recognition (OCR) used in real environments, such as gas-meters and electricity-meters, where the quantity of noise is sometimes as large as the quantity of good signal. Our method combines two algorithms an artificial neural network on one hand, and the k-nearest neighbor as the confirmation algorithm. Our approach, unlike other OCR systems, it is based on the angles of the digits rather than on pixels. Some of the advantages of the proposed system are: insensitivity to the possible rotations of the digits, the possibility to work in different light and exposure conditions, the ability to deduct and use heuristics for character recognition. The experimental results point out that our method with moderate level of training epochs can produce a high accuracy of 99.3 % in recognizing the digits, proving that our system is very successful.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000028
- to stream PascalFrancis, to step Curation: 000736
- to stream PascalFrancis, to step Checkpoint: 000033
- to stream Main, to step Merge: 000193
- to stream Main, to step Curation: 000190
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Optical character recognition in real environments using neural networks and k-nearest neighbor</title><author><name sortKey="Matei, O" sort="Matei, O" uniqKey="Matei O" first="O." last="Matei">O. Matei</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Dept. of Electrical Engineering, North University Center of Baia Mare, Technical University of Cluj-Napoca, Str. V. Babes</s1><s2>430083 Baia Mare</s2><s3>ROU</s3><sZ>1 aut.</sZ></inist:fA14><country>Roumanie</country><wicri:noRegion>430083 Baia Mare</wicri:noRegion></affiliation></author><author><name sortKey="Pop, P C" sort="Pop, P C" uniqKey="Pop P" first="P. C." last="Pop">P. C. Pop</name><affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Dept. of Mathematics and Computer Science, North University Center of Baia Mare, Technical University of Cluj-Napoca, Str. Victoriei</s1><s2>430122 Baia Mare</s2><s3>ROU</s3><sZ>2 aut.</sZ></inist:fA14><country>Roumanie</country><wicri:noRegion>430122 Baia Mare</wicri:noRegion></affiliation></author><author><name sortKey="Valean, H" sort="Valean, H" uniqKey="Valean H" first="H." last="Valean">H. Valean</name><affiliation wicri:level="1"><inist:fA14 i1="03"><s1>Dept. of Automation, Technical University of Cluj-Napoca, Str. G. Baritiu nr. 26-28</s1><s2>Cluj-Napoca</s2><s3>ROU</s3><sZ>3 aut.</sZ></inist:fA14><country>Roumanie</country><wicri:noRegion>Cluj-Napoca</wicri:noRegion></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">INIST</idno><idno type="inist">14-0020736</idno><date when="2013">2013</date><idno type="stanalyst">PASCAL 14-0020736 INIST</idno><idno type="RBID">Pascal:14-0020736</idno><idno type="wicri:Area/PascalFrancis/Corpus">000028</idno><idno type="wicri:Area/PascalFrancis/Curation">000736</idno><idno type="wicri:Area/PascalFrancis/Checkpoint">000033</idno><idno type="wicri:doubleKey">0924-669X:2013:Matei O:optical:character:recognition</idno><idno type="wicri:Area/Main/Merge">000193</idno><idno type="wicri:Area/Main/Curation">000190</idno><idno type="wicri:Area/Main/Exploration">000190</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Optical character recognition in real environments using neural networks and k-nearest neighbor</title><author><name sortKey="Matei, O" sort="Matei, O" uniqKey="Matei O" first="O." last="Matei">O. Matei</name><affiliation wicri:level="1"><inist:fA14 i1="01"><s1>Dept. of Electrical Engineering, North University Center of Baia Mare, Technical University of Cluj-Napoca, Str. V. Babes</s1><s2>430083 Baia Mare</s2><s3>ROU</s3><sZ>1 aut.</sZ></inist:fA14><country>Roumanie</country><wicri:noRegion>430083 Baia Mare</wicri:noRegion></affiliation></author><author><name sortKey="Pop, P C" sort="Pop, P C" uniqKey="Pop P" first="P. C." last="Pop">P. C. Pop</name><affiliation wicri:level="1"><inist:fA14 i1="02"><s1>Dept. of Mathematics and Computer Science, North University Center of Baia Mare, Technical University of Cluj-Napoca, Str. Victoriei</s1><s2>430122 Baia Mare</s2><s3>ROU</s3><sZ>2 aut.</sZ></inist:fA14><country>Roumanie</country><wicri:noRegion>430122 Baia Mare</wicri:noRegion></affiliation></author><author><name sortKey="Valean, H" sort="Valean, H" uniqKey="Valean H" first="H." last="Valean">H. Valean</name><affiliation wicri:level="1"><inist:fA14 i1="03"><s1>Dept. of Automation, Technical University of Cluj-Napoca, Str. G. Baritiu nr. 26-28</s1><s2>Cluj-Napoca</s2><s3>ROU</s3><sZ>3 aut.</sZ></inist:fA14><country>Roumanie</country><wicri:noRegion>Cluj-Napoca</wicri:noRegion></affiliation></author></analytic><series><title level="j" type="main">Applied intelligence : (Boston)</title><title level="j" type="abbreviated">Appl. intell. : (Boston)</title><idno type="ISSN">0924-669X</idno><imprint><date when="2013">2013</date></imprint></series></biblStruct></sourceDesc><seriesStmt><title level="j" type="main">Applied intelligence : (Boston)</title><title level="j" type="abbreviated">Appl. intell. : (Boston)</title><idno type="ISSN">0924-669X</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Character recognition</term><term>Electricity meter</term><term>Experimental result</term><term>Heuristic method</term><term>High precision</term><term>Image processing</term><term>Nearest neighbour</term><term>Neural network</term><term>Optical character recognition</term><term>Pattern recognition</term><term>Pixel</term></keywords><keywords scheme="Pascal" xml:lang="fr"><term>Reconnaissance optique caractère</term><term>Plus proche voisin</term><term>Reconnaissance caractère</term><term>Reconnaissance forme</term><term>Traitement image</term><term>Compteur électrique</term><term>Pixel</term><term>Précision élevée</term><term>Réseau neuronal</term><term>Méthode heuristique</term><term>Résultat expérimental</term><term>.</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">In this paper, we propose a novel process to optical character recognition (OCR) used in real environments, such as gas-meters and electricity-meters, where the quantity of noise is sometimes as large as the quantity of good signal. Our method combines two algorithms an artificial neural network on one hand, and the k-nearest neighbor as the confirmation algorithm. Our approach, unlike other OCR systems, it is based on the angles of the digits rather than on pixels. Some of the advantages of the proposed system are: insensitivity to the possible rotations of the digits, the possibility to work in different light and exposure conditions, the ability to deduct and use heuristics for character recognition. The experimental results point out that our method with moderate level of training epochs can produce a high accuracy of 99.3 % in recognizing the digits, proving that our system is very successful.</div></front></TEI><affiliations><list><country><li>Roumanie</li></country></list><tree><country name="Roumanie"><noRegion><name sortKey="Matei, O" sort="Matei, O" uniqKey="Matei O" first="O." last="Matei">O. Matei</name></noRegion><name sortKey="Pop, P C" sort="Pop, P C" uniqKey="Pop P" first="P. C." last="Pop">P. C. Pop</name><name sortKey="Valean, H" sort="Valean, H" uniqKey="Valean H" first="H." last="Valean">H. Valean</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000190 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000190 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= Pascal:14-0020736
|texte= Optical character recognition in real environments using neural networks and k-nearest neighbor
}}
| This area was generated with Dilib version V0.6.32. |  |