Recognizing Cursive Typewritten Text Using Segmentation-Free System
Identifieur interne : 000037 ( Main/Exploration ); précédent : 000036; suivant : 000038Recognizing Cursive Typewritten Text Using Segmentation-Free System
Auteurs : Mohammad S. Khorsheed [Arabie saoudite]Source :
- The Scientific World Journal [ 2356-6140 ] ; 2015.
Abstract
Feature extraction plays an important role in text recognition as it aims to capture essential characteristics of the text image. Feature extraction algorithms widely range between robust and hard to extract features and noise sensitive and easy to extract features. Among those feature types are statistical features which are derived from the statistical distribution of the image pixels. This paper presents a novel method for feature extraction where simple statistical features are extracted from a one-pixel wide window that slides across the text line. The feature set is clustered in the feature space using vector quantization. The feature vector sequence is then injected to a classification engine for training and recognition purposes. The recognition system is applied to a data corpus which includes cursive Arabic text of more than 600 A4-size sheets typewritten in multiple computer-generated fonts. The system performance is compared to a previously published system from the literature with a similar engine but a different feature set.
Url:
DOI: 10.1155/2015/818432
PubMed: 25961075
PubMed Central: 4413039
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Pmc, to step Corpus: 000018
- to stream Pmc, to step Curation: 000018
- to stream Pmc, to step Checkpoint: 000017
- to stream Ncbi, to step Merge: 000229
- to stream Ncbi, to step Curation: 000229
- to stream Ncbi, to step Checkpoint: 000229
- to stream Main, to step Merge: 000035
- to stream Main, to step Curation: 000037
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Recognizing Cursive Typewritten Text Using Segmentation-Free System</title><author><name sortKey="Khorsheed, Mohammad S" sort="Khorsheed, Mohammad S" uniqKey="Khorsheed M" first="Mohammad S." last="Khorsheed">Mohammad S. Khorsheed</name><affiliation wicri:level="1"><nlm:aff id="I1">National Center for Robotics and Intelligent Systems, King Abdulaziz City for Science & Technology, P.O. Box 6086, Riyadh 11442, Saudi Arabia</nlm:aff><country xml:lang="fr">Arabie saoudite</country><wicri:regionArea>National Center for Robotics and Intelligent Systems, King Abdulaziz City for Science & Technology, P.O. Box 6086, Riyadh 11442</wicri:regionArea><wicri:noRegion>Riyadh 11442</wicri:noRegion></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PMC</idno><idno type="pmid">25961075</idno><idno type="pmc">4413039</idno><idno type="url">http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4413039</idno><idno type="RBID">PMC:4413039</idno><idno type="doi">10.1155/2015/818432</idno><date when="2015">2015</date><idno type="wicri:Area/Pmc/Corpus">000018</idno><idno type="wicri:Area/Pmc/Curation">000018</idno><idno type="wicri:Area/Pmc/Checkpoint">000017</idno><idno type="wicri:Area/Ncbi/Merge">000229</idno><idno type="wicri:Area/Ncbi/Curation">000229</idno><idno type="wicri:Area/Ncbi/Checkpoint">000229</idno><idno type="wicri:doubleKey">2356-6140:2015:Khorsheed M:recognizing:cursive:typewritten</idno><idno type="wicri:Area/Main/Merge">000035</idno><idno type="wicri:Area/Main/Curation">000037</idno><idno type="wicri:Area/Main/Exploration">000037</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a" type="main">Recognizing Cursive Typewritten Text Using Segmentation-Free System</title><author><name sortKey="Khorsheed, Mohammad S" sort="Khorsheed, Mohammad S" uniqKey="Khorsheed M" first="Mohammad S." last="Khorsheed">Mohammad S. Khorsheed</name><affiliation wicri:level="1"><nlm:aff id="I1">National Center for Robotics and Intelligent Systems, King Abdulaziz City for Science & Technology, P.O. Box 6086, Riyadh 11442, Saudi Arabia</nlm:aff><country xml:lang="fr">Arabie saoudite</country><wicri:regionArea>National Center for Robotics and Intelligent Systems, King Abdulaziz City for Science & Technology, P.O. Box 6086, Riyadh 11442</wicri:regionArea><wicri:noRegion>Riyadh 11442</wicri:noRegion></affiliation></author></analytic><series><title level="j">The Scientific World Journal</title><idno type="ISSN">2356-6140</idno><idno type="eISSN">1537-744X</idno><imprint><date when="2015">2015</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en"><p>Feature extraction plays an important role in text recognition as it aims to capture essential characteristics of the text image. Feature extraction algorithms widely range between robust and hard to extract features and noise sensitive and easy to extract features. Among those feature types are statistical features which are derived from the statistical distribution of the image pixels. This paper presents a novel method for feature extraction where simple statistical features are extracted from a one-pixel wide window that slides across the text line. The feature set is clustered in the feature space using vector quantization. The feature vector sequence is then injected to a classification engine for training and recognition purposes. The recognition system is applied to a data corpus which includes cursive Arabic text of more than 600 A4-size sheets typewritten in multiple computer-generated fonts. The system performance is compared to a previously published system from the literature with a similar engine but a different feature set.</p></div></front><back><div1 type="bibliography"><listBibl><biblStruct><analytic><author><name sortKey="Govindan, V K" uniqKey="Govindan V">V. K. Govindan</name></author><author><name sortKey="Shivaprasad, A P" uniqKey="Shivaprasad A">A. P. Shivaprasad</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Downton, A" uniqKey="Downton A">A. Downton</name></author><author><name sortKey="Tregidgo, R W" uniqKey="Tregidgo R">R. W. Tregidgo</name></author><author><name sortKey="Leedham, C G" uniqKey="Leedham C">C. G. Leedham</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Cracknell, C" uniqKey="Cracknell C">C. Cracknell</name></author><author><name sortKey="Downton, A C" uniqKey="Downton A">A. C. Downton</name></author><author><name sortKey="Du, L" uniqKey="Du L">L. Du</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Guillevic, D" uniqKey="Guillevic D">D. Guillevic</name></author><author><name sortKey="Suen, C Y" uniqKey="Suen C">C. Y. Suen</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Amin, A" uniqKey="Amin A">A. Amin</name></author><author><name sortKey="Mansoor, W" uniqKey="Mansoor W">W. Mansoor</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Fadhel, E A" uniqKey="Fadhel E">E. A. Fadhel</name></author><author><name sortKey="Bhattacharyya, P" uniqKey="Bhattacharyya P">P. Bhattacharyya</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Khorsheed, M S" uniqKey="Khorsheed M">M. S. Khorsheed</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Alkhateeb, J H" uniqKey="Alkhateeb J">J. H. AlKhateeb</name></author><author><name sortKey="Ren, J" uniqKey="Ren J">J. Ren</name></author><author><name sortKey="Jiang, J" uniqKey="Jiang J">J. Jiang</name></author><author><name sortKey="Ipson, S" uniqKey="Ipson S">S. Ipson</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Albakoor, M" uniqKey="Albakoor M">M. Albakoor</name></author><author><name sortKey="Saeed, K" uniqKey="Saeed K">K. Saeed</name></author><author><name sortKey="Sukkar, F" uniqKey="Sukkar F">F. Sukkar</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Khorsheed, M S" uniqKey="Khorsheed M">M. S. Khorsheed</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Parker, J" uniqKey="Parker J">J. Parker</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Simon, J" uniqKey="Simon J">J. Simon</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Goraine, H" uniqKey="Goraine H">H. Goraine</name></author><author><name sortKey="Usher, M" uniqKey="Usher M">M. Usher</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Khorsheed, M S" uniqKey="Khorsheed M">M. S. Khorsheed</name></author><author><name sortKey="Clocksin, W F" uniqKey="Clocksin W">W. F. Clocksin</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Amin, A" uniqKey="Amin A">A. Amin</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Benouareth, A" uniqKey="Benouareth A">A. Benouareth</name></author><author><name sortKey="Ennaji, A" uniqKey="Ennaji A">A. Ennaji</name></author><author><name sortKey="Sellami, M" uniqKey="Sellami M">M. Sellami</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Bazzi, I" uniqKey="Bazzi I">I. Bazzi</name></author><author><name sortKey="Schwartz, R" uniqKey="Schwartz R">R. Schwartz</name></author><author><name sortKey="Makhoul, J" uniqKey="Makhoul J">J. Makhoul</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Fehri, M" uniqKey="Fehri M">M. Fehri</name></author><author><name sortKey="Ahmed, M" uniqKey="Ahmed M">M. Ahmed</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Hu, M" uniqKey="Hu M">M. Hu</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="El Khaly, F" uniqKey="El Khaly F">F. El-Khaly</name></author><author><name sortKey="Sid Ahmed, M A" uniqKey="Sid Ahmed M">M. A. Sid-Ahmed</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Mahmoud, S A" uniqKey="Mahmoud S">S. A. Mahmoud</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Khorsheed, M S" uniqKey="Khorsheed M">M. S. Khorsheed</name></author><author><name sortKey="Clocksin, W F" uniqKey="Clocksin W">W. F. Clocksin</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Freeman, H" uniqKey="Freeman H">H. Freeman</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Amin, A" uniqKey="Amin A">A. Amin</name></author><author><name sortKey="Mari, J F" uniqKey="Mari J">J. F. Mari</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Osman, Z" uniqKey="Osman Z">Z. Osman</name></author><author><name sortKey="Hamandi, L" uniqKey="Hamandi L">L. Hamandi</name></author><author><name sortKey="Zantout, R" uniqKey="Zantout R">R. Zantout</name></author><author><name sortKey="Sibai, F N" uniqKey="Sibai F">F. N. Sibai</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Alginahi, Y M" uniqKey="Alginahi Y">Y. M. Alginahi</name></author><author><name sortKey="Siddiqi, A A" uniqKey="Siddiqi A">A. A. Siddiqi</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Mutter, K N" uniqKey="Mutter K">K. N. Mutter</name></author><author><name sortKey="Jafri, M Z M" uniqKey="Jafri M">M. Z. M. Jafri</name></author><author><name sortKey="Aziz, A A" uniqKey="Aziz A">A. A. Aziz</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Baccour, L" uniqKey="Baccour L">L. Baccour</name></author><author><name sortKey="Alimi, A M" uniqKey="Alimi A">A. M. Alimi</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Aljuaid, H" uniqKey="Aljuaid H">H. Aljuaid</name></author><author><name sortKey="Mohamad, D" uniqKey="Mohamad D">D. Mohamad</name></author><author><name sortKey="Sarfraz, M" uniqKey="Sarfraz M">M. Sarfraz</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Rabiner, L" uniqKey="Rabiner L">L. Rabiner</name></author><author><name sortKey="Juang, B H" uniqKey="Juang B">B.-H. Juang</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Biadsy, F" uniqKey="Biadsy F">F. Biadsy</name></author><author><name sortKey="El Sana, J" uniqKey="El Sana J">J. El-Sana</name></author><author><name sortKey="Habash, N" uniqKey="Habash N">N. Habash</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Alkhateeb, J H" uniqKey="Alkhateeb J">J. H. Alkhateeb</name></author><author><name sortKey="Ren, J" uniqKey="Ren J">J. Ren</name></author><author><name sortKey="Jiang, J" uniqKey="Jiang J">J. Jiang</name></author><author><name sortKey="Al Muhtaseb, H" uniqKey="Al Muhtaseb H">H. Al-Muhtaseb</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Young, S" uniqKey="Young S">S. Young</name></author><author><name sortKey="Evermann, G" uniqKey="Evermann G">G. Evermann</name></author><author><name sortKey="Gales, M J F" uniqKey="Gales M">M. J. F. Gales</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Gray, R M" uniqKey="Gray R">R. M. Gray</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Khorsheed, M S" uniqKey="Khorsheed M">M. S. Khorsheed</name></author><author><name sortKey="Al Omari, H K" uniqKey="Al Omari H">H. K. Al-Omari</name></author><author><name sortKey="Alfaifi, K M" uniqKey="Alfaifi K">K. M. Alfaifi</name></author><author><name sortKey="Alhazmi, K M" uniqKey="Alhazmi K">K. M. Alhazmi</name></author></analytic></biblStruct></listBibl></div1></back></TEI><affiliations><list><country><li>Arabie saoudite</li></country></list><tree><country name="Arabie saoudite"><noRegion><name sortKey="Khorsheed, Mohammad S" sort="Khorsheed, Mohammad S" uniqKey="Khorsheed M" first="Mohammad S." last="Khorsheed">Mohammad S. Khorsheed</name></noRegion></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 000037 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000037 | 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= PMC:4413039
|texte= Recognizing Cursive Typewritten Text Using Segmentation-Free System
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i -Sk "pubmed:25961075" \
| HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd \
| NlmPubMed2Wicri -a OcrV1
| This area was generated with Dilib version V0.6.32. |  |