OcrV1, Main, Exploration, bibRecord, 001375

Sequential neural network combination for degraded machine printed character recognition

Identifieur interne : 001375 ( Main/Exploration ); précédent : 001374; suivant : 001376

Sequential neural network combination for degraded machine printed character recognition

Auteurs : Abderrahmane Namane [France, Algérie] ; Madjid Arezki [Algérie] ; Abderrezak Guessoum [Algérie] ; El Houssine Soubari [France] ; Patrick Meyrueis ; Michel Bruynooghe [France]

Source :

SPIE proceedings series [ 1017-2653 ] ; 2005.

RBID : Pascal:05-0360305

Descripteurs français

Pascal (Inist)
- Réseau neuronal, Caractère imprimé, Reconnaissance caractère, Reconnaissance optique caractère, Modèle Hopfield, Réseau multicouche, Perceptron, Prototype, Traitement image, Méthode itérative, Précision, Chèque bancaire, Réseau neuronal Hopfield, Classification automatique, Bruit additif, Bruit gaussien, Niveau bruit, Reconnaissance forme, Classification signal, Extraction caractéristique, Traitement signal.
Wicri :
- topic : Prototype.

English descriptors

KwdEn :
- Accuracy, Additive noise, Automatic classification, Bank check, Character recognition, Feature extraction, Gaussian noise, Hopfield model, Hopfield neural nets, Image processing, Iterative method, Multilayer network, Neural network, Noise level, Optical character recognition, Pattern recognition, Perceptron, Printed character, Prototype, Signal classification, Signal processing.

Abstract

This paper presents an OCR method that combines Hopfield network with two layer perceptron for degraded printed character recognition. Hopfield network stores 35 prototype characters used as main classes. After the pre-processing, an image of a character is given to Hopfield network which can yield after a fixed iteration number, a pattern that is subsequently fed to MLP for classification. The main idea is to enhance or restore such degraded character images with Hopfield model at different iteration number for recognition accuracy applied to poor quality bank check. We report experimental results for a comparison of three neural architectures: the Hopfield network, the MLP-based classifier and the proposed combined architecture. Classification accuracy for ten digits and twenty five alphabetic characters from a single font is also studied in the presence of additive Gaussian noise. The paper reports 100% recognition rate at different levels of noise. Experimental results show an achievement of 99.35 % of recognition rate on poor quality bank check characters, which confirm that the proposed approach can be successfully used for effective degraded printed character recognition.

Affiliations:

Links toward previous steps (curation, corpus...)

to stream PascalFrancis, to step Corpus: 000459
to stream PascalFrancis, to step Curation: 000329
to stream PascalFrancis, to step Checkpoint: 000382
to stream Main, to step Merge: 001412
to stream Main, to step Curation: 001375

Le document en format XML

<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Sequential neural network combination for degraded machine printed character recognition</title>
<author><name sortKey="Namane, Abderrahmane" sort="Namane, Abderrahmane" uniqKey="Namane A" first="Abderrahmane" last="Namane">Abderrahmane Namane</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Université Louis Pasteur, Ecole Nationale Supérieure de Physique, Laboratoire des Systèmes Photoniques, b1d. S. Brant</s1>
<s2>67 400 Illkirch, Strasbourg</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><settlement type="city">Strasbourg</settlement>
</placeName>
<orgName type="university">Université Strasbourg 1</orgName>
<placeName><settlement type="city">Strasbourg</settlement>
<region type="region" nuts="2">Alsace</region>
</placeName>
</affiliation>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>University de Blida, Faculté des sciences de l'ingénieur, département d'Electro nique, Laboratoire de Traitement du Signal et de l'Image (LATSI), BP. 270, route de Soumaâ</s1>
<s2>Blida</s2>
<s3>DZA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Algérie</country>
<wicri:noRegion>Blida</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Arezki, Madjid" sort="Arezki, Madjid" uniqKey="Arezki M" first="Madjid" last="Arezki">Madjid Arezki</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>University de Blida, Faculté des sciences de l'ingénieur, département d'Electro nique, Laboratoire de Traitement du Signal et de l'Image (LATSI), BP. 270, route de Soumaâ</s1>
<s2>Blida</s2>
<s3>DZA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Algérie</country>
<wicri:noRegion>Blida</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Guessoum, Abderrezak" sort="Guessoum, Abderrezak" uniqKey="Guessoum A" first="Abderrezak" last="Guessoum">Abderrezak Guessoum</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>University de Blida, Faculté des sciences de l'ingénieur, département d'Electro nique, Laboratoire de Traitement du Signal et de l'Image (LATSI), BP. 270, route de Soumaâ</s1>
<s2>Blida</s2>
<s3>DZA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Algérie</country>
<wicri:noRegion>Blida</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Soubari, El Houssine" sort="Soubari, El Houssine" uniqKey="Soubari E" first="El Houssine" last="Soubari">El Houssine Soubari</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Université Louis Pasteur, Ecole Nationale Supérieure de Physique, Laboratoire des Systèmes Photoniques, b1d. S. Brant</s1>
<s2>67 400 Illkirch, Strasbourg</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><settlement type="city">Strasbourg</settlement>
</placeName>
<orgName type="university">Université Strasbourg 1</orgName>
<placeName><settlement type="city">Strasbourg</settlement>
<region type="region" nuts="2">Alsace</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Meyrueis, Patrick" sort="Meyrueis, Patrick" uniqKey="Meyrueis P" first="Patrick" last="Meyrueis">Patrick Meyrueis</name>
</author>
<author><name sortKey="Bruynooghe, Michel" sort="Bruynooghe, Michel" uniqKey="Bruynooghe M" first="Michel" last="Bruynooghe">Michel Bruynooghe</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Université Louis Pasteur, Ecole Nationale Supérieure de Physique, Laboratoire des Systèmes Photoniques, b1d. S. Brant</s1>
<s2>67 400 Illkirch, Strasbourg</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><settlement type="city">Strasbourg</settlement>
</placeName>
<orgName type="university">Université Strasbourg 1</orgName>
<placeName><settlement type="city">Strasbourg</settlement>
<region type="region" nuts="2">Alsace</region>
</placeName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">05-0360305</idno>
<date when="2005">2005</date>
<idno type="stanalyst">PASCAL 05-0360305 INIST</idno>
<idno type="RBID">Pascal:05-0360305</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000459</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000329</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000382</idno>
<idno type="wicri:doubleKey">1017-2653:2005:Namane A:sequential:neural:network</idno>
<idno type="wicri:Area/Main/Merge">001412</idno>
<idno type="wicri:Area/Main/Curation">001375</idno>
<idno type="wicri:Area/Main/Exploration">001375</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Sequential neural network combination for degraded machine printed character recognition</title>
<author><name sortKey="Namane, Abderrahmane" sort="Namane, Abderrahmane" uniqKey="Namane A" first="Abderrahmane" last="Namane">Abderrahmane Namane</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Université Louis Pasteur, Ecole Nationale Supérieure de Physique, Laboratoire des Systèmes Photoniques, b1d. S. Brant</s1>
<s2>67 400 Illkirch, Strasbourg</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><settlement type="city">Strasbourg</settlement>
</placeName>
<orgName type="university">Université Strasbourg 1</orgName>
<placeName><settlement type="city">Strasbourg</settlement>
<region type="region" nuts="2">Alsace</region>
</placeName>
</affiliation>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>University de Blida, Faculté des sciences de l'ingénieur, département d'Electro nique, Laboratoire de Traitement du Signal et de l'Image (LATSI), BP. 270, route de Soumaâ</s1>
<s2>Blida</s2>
<s3>DZA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Algérie</country>
<wicri:noRegion>Blida</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Arezki, Madjid" sort="Arezki, Madjid" uniqKey="Arezki M" first="Madjid" last="Arezki">Madjid Arezki</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>University de Blida, Faculté des sciences de l'ingénieur, département d'Electro nique, Laboratoire de Traitement du Signal et de l'Image (LATSI), BP. 270, route de Soumaâ</s1>
<s2>Blida</s2>
<s3>DZA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Algérie</country>
<wicri:noRegion>Blida</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Guessoum, Abderrezak" sort="Guessoum, Abderrezak" uniqKey="Guessoum A" first="Abderrezak" last="Guessoum">Abderrezak Guessoum</name>
<affiliation wicri:level="1"><inist:fA14 i1="02"><s1>University de Blida, Faculté des sciences de l'ingénieur, département d'Electro nique, Laboratoire de Traitement du Signal et de l'Image (LATSI), BP. 270, route de Soumaâ</s1>
<s2>Blida</s2>
<s3>DZA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>Algérie</country>
<wicri:noRegion>Blida</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Soubari, El Houssine" sort="Soubari, El Houssine" uniqKey="Soubari E" first="El Houssine" last="Soubari">El Houssine Soubari</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Université Louis Pasteur, Ecole Nationale Supérieure de Physique, Laboratoire des Systèmes Photoniques, b1d. S. Brant</s1>
<s2>67 400 Illkirch, Strasbourg</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><settlement type="city">Strasbourg</settlement>
</placeName>
<orgName type="university">Université Strasbourg 1</orgName>
<placeName><settlement type="city">Strasbourg</settlement>
<region type="region" nuts="2">Alsace</region>
</placeName>
</affiliation>
</author>
<author><name sortKey="Meyrueis, Patrick" sort="Meyrueis, Patrick" uniqKey="Meyrueis P" first="Patrick" last="Meyrueis">Patrick Meyrueis</name>
</author>
<author><name sortKey="Bruynooghe, Michel" sort="Bruynooghe, Michel" uniqKey="Bruynooghe M" first="Michel" last="Bruynooghe">Michel Bruynooghe</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>Université Louis Pasteur, Ecole Nationale Supérieure de Physique, Laboratoire des Systèmes Photoniques, b1d. S. Brant</s1>
<s2>67 400 Illkirch, Strasbourg</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>4 aut.</sZ>
<sZ>6 aut.</sZ>
</inist:fA14>
<country>France</country>
<placeName><settlement type="city">Strasbourg</settlement>
</placeName>
<orgName type="university">Université Strasbourg 1</orgName>
<placeName><settlement type="city">Strasbourg</settlement>
<region type="region" nuts="2">Alsace</region>
</placeName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
<imprint><date when="2005">2005</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">SPIE proceedings series</title>
<idno type="ISSN">1017-2653</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Accuracy</term>
<term>Additive noise</term>
<term>Automatic classification</term>
<term>Bank check</term>
<term>Character recognition</term>
<term>Feature extraction</term>
<term>Gaussian noise</term>
<term>Hopfield model</term>
<term>Hopfield neural nets</term>
<term>Image processing</term>
<term>Iterative method</term>
<term>Multilayer network</term>
<term>Neural network</term>
<term>Noise level</term>
<term>Optical character recognition</term>
<term>Pattern recognition</term>
<term>Perceptron</term>
<term>Printed character</term>
<term>Prototype</term>
<term>Signal classification</term>
<term>Signal processing</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Réseau neuronal</term>
<term>Caractère imprimé</term>
<term>Reconnaissance caractère</term>
<term>Reconnaissance optique caractère</term>
<term>Modèle Hopfield</term>
<term>Réseau multicouche</term>
<term>Perceptron</term>
<term>Prototype</term>
<term>Traitement image</term>
<term>Méthode itérative</term>
<term>Précision</term>
<term>Chèque bancaire</term>
<term>Réseau neuronal Hopfield</term>
<term>Classification automatique</term>
<term>Bruit additif</term>
<term>Bruit gaussien</term>
<term>Niveau bruit</term>
<term>Reconnaissance forme</term>
<term>Classification signal</term>
<term>Extraction caractéristique</term>
<term>Traitement signal</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Prototype</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">This paper presents an OCR method that combines Hopfield network with two layer perceptron for degraded printed character recognition. Hopfield network stores 35 prototype characters used as main classes. After the pre-processing, an image of a character is given to Hopfield network which can yield after a fixed iteration number, a pattern that is subsequently fed to MLP for classification. The main idea is to enhance or restore such degraded character images with Hopfield model at different iteration number for recognition accuracy applied to poor quality bank check. We report experimental results for a comparison of three neural architectures: the Hopfield network, the MLP-based classifier and the proposed combined architecture. Classification accuracy for ten digits and twenty five alphabetic characters from a single font is also studied in the presence of additive Gaussian noise. The paper reports 100% recognition rate at different levels of noise. Experimental results show an achievement of 99.35 % of recognition rate on poor quality bank check characters, which confirm that the proposed approach can be successfully used for effective degraded printed character recognition.</div>
</front>
</TEI>
<affiliations><list><country><li>Algérie</li>
<li>France</li>
</country>
<region><li>Alsace</li>
</region>
<settlement><li>Strasbourg</li>
</settlement>
<orgName><li>Université Strasbourg 1</li>
</orgName>
</list>
<tree><noCountry><name sortKey="Meyrueis, Patrick" sort="Meyrueis, Patrick" uniqKey="Meyrueis P" first="Patrick" last="Meyrueis">Patrick Meyrueis</name>
</noCountry>
<country name="France"><noRegion><name sortKey="Namane, Abderrahmane" sort="Namane, Abderrahmane" uniqKey="Namane A" first="Abderrahmane" last="Namane">Abderrahmane Namane</name>
</noRegion>
<name sortKey="Bruynooghe, Michel" sort="Bruynooghe, Michel" uniqKey="Bruynooghe M" first="Michel" last="Bruynooghe">Michel Bruynooghe</name>
<name sortKey="Soubari, El Houssine" sort="Soubari, El Houssine" uniqKey="Soubari E" first="El Houssine" last="Soubari">El Houssine Soubari</name>
</country>
<country name="Algérie"><noRegion><name sortKey="Namane, Abderrahmane" sort="Namane, Abderrahmane" uniqKey="Namane A" first="Abderrahmane" last="Namane">Abderrahmane Namane</name>
</noRegion>
<name sortKey="Arezki, Madjid" sort="Arezki, Madjid" uniqKey="Arezki M" first="Madjid" last="Arezki">Madjid Arezki</name>
<name sortKey="Guessoum, Abderrezak" sort="Guessoum, Abderrezak" uniqKey="Guessoum A" first="Abderrezak" last="Guessoum">Abderrezak Guessoum</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 001375 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 001375 | 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:05-0360305
   |texte=   Sequential neural network combination for degraded machine printed character recognition
}}

This area was generated with Dilib version V0.6.32.
Data generation: Sat Nov 11 16:53:45 2017. Site generation: Mon Mar 11 23:15:16 2024

	Serveur d'exploration sur l'OCR
	Attention, ce site est en cours de développement ! Attention, site généré par des moyens informatiques à partir de corpus bruts. Les informations ne sont donc pas validées.

Serveur d'exploration sur l'OCR

Sequential neural network combination for degraded machine printed character recognition

Sequential neural network combination for degraded machine printed character recognition

Source :

Descripteurs français

English descriptors

Abstract

Links toward previous steps (curation, corpus...)

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri