Handwriting Moroccan regions recognition using Tifinagh character
Identifieur interne : 000128 ( Pmc/Curation ); précédent : 000127; suivant : 000129Handwriting Moroccan regions recognition using Tifinagh character
Auteurs : B. El Kessab ; C. Daoui ; B. Bouikhalene ; R. SalouanSource :
- Data in Brief [ 2352-3409 ] ; 2015.
Abstract
The territorial organization of Morocco during administratives division of 2009 is based on 16 regions. In this work we will create a system of recognition of handwritten words (names of regions) using the Amazigh language is an official language by the Moroccan Royal Institute of Amazigh Culture (IRCAM) (2003a)
In this context we propose a data set for handwritten Tifinagh regions composed of 1600 image (100 Image for each region). The dataset can be used in one hand to test the efficiency of the Tifinagh region recognition system in extraction of characteristics significatives and the correct identification of each region in classification phase in the other hand.
Url:
DOI: 10.1016/j.dib.2015.07.018
PubMed: 26966718
PubMed Central: 4783523
Links toward previous steps (curation, corpus...)
- to stream Pmc, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000129
Links to Exploration step
PMC:4783523Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Handwriting Moroccan regions recognition using Tifinagh character</title><author><name sortKey="El Kessab, B" sort="El Kessab, B" uniqKey="El Kessab B" first="B." last="El Kessab">B. El Kessab</name></author><author><name sortKey="Daoui, C" sort="Daoui, C" uniqKey="Daoui C" first="C." last="Daoui">C. Daoui</name></author><author><name sortKey="Bouikhalene, B" sort="Bouikhalene, B" uniqKey="Bouikhalene B" first="B." last="Bouikhalene">B. Bouikhalene</name></author><author><name sortKey="Salouan, R" sort="Salouan, R" uniqKey="Salouan R" first="R." last="Salouan">R. Salouan</name></author></titleStmt><publicationStmt><idno type="wicri:source">PMC</idno><idno type="pmid">26966718</idno><idno type="pmc">4783523</idno><idno type="url">http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4783523</idno><idno type="RBID">PMC:4783523</idno><idno type="doi">10.1016/j.dib.2015.07.018</idno><date when="2015">2015</date><idno type="wicri:Area/Pmc/Corpus">000129</idno><idno type="wicri:explorRef" wicri:stream="Pmc" wicri:step="Corpus" wicri:corpus="PMC">000129</idno><idno type="wicri:Area/Pmc/Curation">000128</idno><idno type="wicri:explorRef" wicri:stream="Pmc" wicri:step="Curation">000128</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a" type="main">Handwriting Moroccan regions recognition using Tifinagh character</title><author><name sortKey="El Kessab, B" sort="El Kessab, B" uniqKey="El Kessab B" first="B." last="El Kessab">B. El Kessab</name></author><author><name sortKey="Daoui, C" sort="Daoui, C" uniqKey="Daoui C" first="C." last="Daoui">C. Daoui</name></author><author><name sortKey="Bouikhalene, B" sort="Bouikhalene, B" uniqKey="Bouikhalene B" first="B." last="Bouikhalene">B. Bouikhalene</name></author><author><name sortKey="Salouan, R" sort="Salouan, R" uniqKey="Salouan R" first="R." last="Salouan">R. Salouan</name></author></analytic><series><title level="j">Data in Brief</title><idno type="eISSN">2352-3409</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>The territorial organization of Morocco during administratives division of 2009 is based on 16 regions. In this work we will create a system of recognition of handwritten words (names of regions) using the Amazigh language is an official language by the Moroccan Royal Institute of Amazigh Culture (IRCAM) (2003a) <xref rid="bib1" ref-type="bibr">[1]</xref> such as this language is slightly treated by researchers in pattern recognition field that is why we decided to study this language (El Kessab et al., 2013 <xref rid="bib3" ref-type="bibr">[3]</xref>; El Kessab et al., 2014 <xref rid="bib4" ref-type="bibr">[4]</xref>) that knowing the state make a decision to computerize the various public sectors by this language.</p><p>In this context we propose a data set for handwritten Tifinagh regions composed of 1600 image (100 Image for each region). The dataset can be used in one hand to test the efficiency of the Tifinagh region recognition system in extraction of characteristics significatives and the correct identification of each region in classification phase in the other hand.</p></div></front><back><div1 type="bibliography"><listBibl><biblStruct></biblStruct><biblStruct></biblStruct><biblStruct><analytic><author><name sortKey="El Kessab, B" uniqKey="El Kessab B">B. El Kessab</name></author><author><name sortKey="Daoui, C" uniqKey="Daoui C">C. Daoui</name></author><author><name sortKey="Bouikhalene, B" uniqKey="Bouikhalene B">B. Bouikhalene</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="El Kessab, B" uniqKey="El Kessab B">B. El Kessab</name></author><author><name sortKey="Daoui, C" uniqKey="Daoui C">C. Daoui</name></author><author><name sortKey="Bouikhalene, B" uniqKey="Bouikhalene B">B. Bouikhalene</name></author><author><name sortKey="Salouan, R" uniqKey="Salouan R">R. Salouan.</name></author></analytic></biblStruct><biblStruct><analytic><author><name sortKey="Sadiqi, Fatima" uniqKey="Sadiqi F">Fatima Sadiqi</name></author></analytic></biblStruct><biblStruct></biblStruct><biblStruct></biblStruct></listBibl></div1></back></TEI><pmc article-type="brief-report"><pmc-dir>properties open_access</pmc-dir>
<front><journal-meta><journal-id journal-id-type="nlm-ta">Data Brief</journal-id><journal-id journal-id-type="iso-abbrev">Data Brief</journal-id><journal-title-group><journal-title>Data in Brief</journal-title></journal-title-group><issn pub-type="epub">2352-3409</issn><publisher><publisher-name>Elsevier</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="pmid">26966718</article-id><article-id pub-id-type="pmc">4783523</article-id><article-id pub-id-type="publisher-id">S2352-3409(15)00137-7</article-id><article-id pub-id-type="doi">10.1016/j.dib.2015.07.018</article-id><article-categories><subj-group subj-group-type="heading"><subject>Data Article</subject></subj-group></article-categories><title-group><article-title>Handwriting Moroccan regions recognition using Tifinagh character</article-title></title-group><contrib-group><contrib contrib-type="author"><name><surname>El Kessab</surname><given-names>B.</given-names></name><email>bade10@hotmail.fr</email></contrib><contrib contrib-type="author"><name><surname>Daoui</surname><given-names>C.</given-names></name></contrib><contrib contrib-type="author"><name><surname>Bouikhalene</surname><given-names>B.</given-names></name></contrib><contrib contrib-type="author"><name><surname>Salouan</surname><given-names>R.</given-names></name></contrib></contrib-group><aff id="aff0005">Laboratory of Information Processing and Decision Support, Morocco</aff><pub-date pub-type="pmc-release"><day>26</day><month>7</month><year>2015</year></pub-date><pmc-comment> PMC Release delay is 0 months and 0 days and was based on .</pmc-comment>
<pub-date pub-type="collection"><month>9</month><year>2015</year></pub-date><pub-date pub-type="epub"><day>26</day><month>7</month><year>2015</year></pub-date><volume>4</volume><fpage>534</fpage><lpage>543</lpage><history><date date-type="received"><day>20</day><month>6</month><year>2015</year></date><date date-type="rev-recd"><day>10</day><month>7</month><year>2015</year></date><date date-type="accepted"><day>13</day><month>7</month><year>2015</year></date></history><permissions><copyright-statement>© 2015 The Authors</copyright-statement><copyright-year>2015</copyright-year><license license-type="CC BY" xlink:href="http://creativecommons.org/licenses/by/4.0/"><license-p>This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).</license-p></license></permissions><abstract><p>The territorial organization of Morocco during administratives division of 2009 is based on 16 regions. In this work we will create a system of recognition of handwritten words (names of regions) using the Amazigh language is an official language by the Moroccan Royal Institute of Amazigh Culture (IRCAM) (2003a) <xref rid="bib1" ref-type="bibr">[1]</xref> such as this language is slightly treated by researchers in pattern recognition field that is why we decided to study this language (El Kessab et al., 2013 <xref rid="bib3" ref-type="bibr">[3]</xref>; El Kessab et al., 2014 <xref rid="bib4" ref-type="bibr">[4]</xref>) that knowing the state make a decision to computerize the various public sectors by this language.</p><p>In this context we propose a data set for handwritten Tifinagh regions composed of 1600 image (100 Image for each region). The dataset can be used in one hand to test the efficiency of the Tifinagh region recognition system in extraction of characteristics significatives and the correct identification of each region in classification phase in the other hand.</p></abstract></article-meta></front><floats-group><fig id="f0005"><label>Fig. 1</label><caption><p>The proposed system for handwritten Tifinagh words recognition.</p></caption><graphic xlink:href="gr1"></graphic></fig><fig id="f0010"><label>Fig. 2</label><caption><p>Comparison between the Tifinagh, Arabic and Latin characters.</p></caption><graphic xlink:href="gr2"></graphic></fig><fig id="f0015"><label>Fig. 3</label><caption><p>Sixteen regions with Amazigh language.</p></caption><graphic xlink:href="gr3"></graphic></fig><fig id="f0020"><label>Fig. 4</label><caption><p>Example of handwritten Tifinagh region from the proposed data base.</p></caption><graphic xlink:href="gr4"></graphic></fig><fig id="f0025"><label>Fig. 5</label><caption><p>The graphical representation of recognition rate τr for each region.</p></caption><graphic xlink:href="gr5"></graphic></fig><fig id="f0030"><label>Fig. 6</label><caption><p>The original image.</p></caption><graphic xlink:href="gr6"></graphic></fig><fig id="f0035"><label>Fig. 7</label><caption><p>Graphical representation of segmentation column.</p></caption><graphic xlink:href="gr7"></graphic></fig><fig id="f0040"><label>Fig.8</label><caption><p>The segmentation in columns.</p></caption><graphic xlink:href="gr8"></graphic></fig><fig id="f0045"><label>Fig. 9</label><caption><p>The square zoning method.</p></caption><graphic xlink:href="gr9"></graphic></fig><fig id="f0050"><label>Fig. 10</label><caption><p>Processes of feature extraction by square zoning.</p></caption><graphic xlink:href="gr10"></graphic></fig><fig id="f0055"><label>Fig. 11</label><caption><p>The triangular zoning method.</p></caption><graphic xlink:href="gr11"></graphic></fig><fig id="f0060"><label>Fig. 12</label><caption><p>Processes of feature extraction by triangular zoning.</p></caption><graphic xlink:href="gr12"></graphic></fig><fig id="f0065"><label>Fig. 13</label><caption><p>The determination of optimal hyperplane, vectors supports, maximum Marge and valid hyperplanes.</p></caption><graphic xlink:href="gr13"></graphic></fig><fig id="f0070"><label>Fig. 14</label><caption><p>The multi-layer perceptron.</p></caption><graphic xlink:href="gr14"></graphic></fig><fig id="f0075"><label>Fig. 15</label><caption><p>The graphical representation of recognition rate <italic>τ</italic><sub>r</sub> of each region with all methods.</p></caption><graphic xlink:href="gr15"></graphic></fig><fig id="f0080"><label>Fig. 16</label><caption><p>The graphical representation of recognition rate <italic>τ</italic><sub>r</sub> of all feature extraction methods.</p></caption><graphic xlink:href="gr16"></graphic></fig><fig id="f0085"><label>Fig. 17</label><caption><p>The graphical representation of recognition rate <italic>τ</italic><sub>r</sub> of square zoning method and SVM classifier.</p></caption><graphic xlink:href="gr17"></graphic></fig><table-wrap id="t0005" position="float"><label>Table 1</label><caption><p>The obtained recognition rates <italic>τ</italic><sub>r</sub> and <italic>τ</italic><sub>g</sub> by each hybrid method and each classifier.</p></caption><table frame="hsides" rules="groups"><thead><tr><th align="center"><bold>Regions</bold></th><th colspan="2" align="center"><bold>Neural networks</bold><hr></hr></th><th colspan="2" align="center"><bold>Support vectors machines</bold><hr></hr></th></tr><tr><th align="left"><bold>Square zoning</bold></th><th align="left"><bold>Triangular zoning</bold></th><th align="left"><bold>Square zoning</bold></th><th align="left"><bold>Triangular zoning</bold></th></tr></thead><tbody><tr><td align="center"><inline-graphic xlink:href="fx1.gif"></inline-graphic></td><td align="char">70.00</td><td align="char">67.57</td><td align="char">82.00</td><td align="char">74.49</td></tr><tr><td align="center"><inline-graphic xlink:href="fx2.gif"></inline-graphic></td><td align="char">79.13</td><td align="char">73.4</td><td align="char">80.00</td><td align="char">75.18</td></tr><tr><td align="center"><inline-graphic xlink:href="fx3.gif"></inline-graphic></td><td align="char">60.00</td><td align="char">60.74</td><td align="char">83.00</td><td align="char">80.34</td></tr><tr><td align="center"><inline-graphic xlink:href="fx4.gif"></inline-graphic></td><td align="char">55.09</td><td align="char">53.48</td><td align="char">76.67</td><td align="char">70.61</td></tr><tr><td align="center"><inline-graphic xlink:href="fx5.gif"></inline-graphic></td><td align="char">65.21</td><td align="char">64.00</td><td align="char">74.00</td><td align="char">70.78</td></tr><tr><td align="center"><inline-graphic xlink:href="fx6.gif"></inline-graphic></td><td align="char">63.25</td><td align="char">65.85</td><td align="char">69.00</td><td align="char">66.60</td></tr><tr><td align="center"><inline-graphic xlink:href="fx7.gif"></inline-graphic></td><td align="char">50.18</td><td align="char">50.97</td><td align="char">68.67</td><td align="char">65.00</td></tr><tr><td align="center"><inline-graphic xlink:href="fx8.gif"></inline-graphic></td><td align="char">69.66</td><td align="char">65.93</td><td align="char">71.67</td><td align="char">70.56</td></tr><tr><td align="center"><inline-graphic xlink:href="fx9.gif"></inline-graphic></td><td align="char">64.46</td><td align="char">61.71</td><td align="char">67.00</td><td align="char">63.60</td></tr><tr><td align="center"><inline-graphic xlink:href="fx10.gif"></inline-graphic></td><td align="char">71.31</td><td align="char">67.40</td><td align="char">72.00</td><td align="char">70.96</td></tr><tr><td align="center"><inline-graphic xlink:href="fx11.gif"></inline-graphic></td><td align="char">73.00</td><td align="char">71.43</td><td align="char">74.00</td><td align="char">71.73</td></tr><tr><td align="center"><inline-graphic xlink:href="fx12.gif"></inline-graphic></td><td align="char">66.11</td><td align="char">64.84</td><td align="char">67.57</td><td align="char">69.41</td></tr><tr><td align="center"><inline-graphic xlink:href="fx13.gif"></inline-graphic></td><td align="char">68.67</td><td align="char">62.69</td><td align="char">70.40</td><td align="char">69.00</td></tr><tr><td align="center"><inline-graphic xlink:href="fx14.gif"></inline-graphic></td><td align="char">73.37</td><td align="char">69.29</td><td align="char">72.74</td><td align="char">70.44</td></tr><tr><td align="center"><inline-graphic xlink:href="fx15.gif"></inline-graphic></td><td align="char">67.45</td><td align="char">66.04</td><td align="char">69.48</td><td align="char">61.33</td></tr><tr><td align="center"><inline-graphic xlink:href="fx16.gif"></inline-graphic></td><td align="char">69.26</td><td align="char">68.34</td><td align="char">81.4</td><td align="char">74.18</td></tr><tr><td align="center"><italic>τ</italic><sub><italic>g</italic></sub></td><td align="char">66.64</td><td align="char">64.61</td><td align="char">73.73</td><td align="char">70.26</td></tr></tbody></table><table-wrap-foot><fn><p>All values of the recognition rate for each region <italic>τ</italic><sub>r</sub> (given in %) and also those of the global rate recognition <italic>τ</italic><sub><italic>g</italic></sub> of all 16 regions (given in %) which we have obtained in the table.</p></fn></table-wrap-foot></table-wrap></floats-group></pmc></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Linguistique/explor/TamazightV2/Data/Pmc/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000128 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Pmc/Curation/biblio.hfd -nk 000128 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Linguistique
|area= TamazightV2
|flux= Pmc
|étape= Curation
|type= RBID
|clé= PMC:4783523
|texte= Handwriting Moroccan regions recognition using Tifinagh character
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Pmc/Curation/RBID.i -Sk "pubmed:26966718" \
| HfdSelect -Kh $EXPLOR_AREA/Data/Pmc/Curation/biblio.hfd \
| NlmPubMed2Wicri -a TamazightV2
| This area was generated with Dilib version V0.6.33. |  |