Links to Exploration step
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Data set for Tifinagh handwriting character recognition</title>
<author><name sortKey="Bencharef, Omar" sort="Bencharef, Omar" uniqKey="Bencharef O" first="Omar" last="Bencharef">Omar Bencharef</name>
<affiliation><nlm:aff id="aff0005">Higher School of Technology-Essaouira, Cadi Ayyad University, Marrakech, Morocco</nlm:aff>
</affiliation>
</author>
<author><name sortKey="Chihab, Younes" sort="Chihab, Younes" uniqKey="Chihab Y" first="Younes" last="Chihab">Younes Chihab</name>
<affiliation><nlm:aff id="aff0010">FP Safi, Cadi Ayyad University, Marrakech, Morocco</nlm:aff>
</affiliation>
</author>
<author><name sortKey="Mousaid, Nouredine" sort="Mousaid, Nouredine" uniqKey="Mousaid N" first="Nouredine" last="Mousaid">Nouredine Mousaid</name>
<affiliation><nlm:aff id="aff0005">Higher School of Technology-Essaouira, Cadi Ayyad University, Marrakech, Morocco</nlm:aff>
</affiliation>
</author>
<author><name sortKey="Oujaoura, Mustapha" sort="Oujaoura, Mustapha" uniqKey="Oujaoura M" first="Mustapha" last="Oujaoura">Mustapha Oujaoura</name>
<affiliation><nlm:aff id="aff0015">Faculty of Science and Technology, Sultan Moulay Slimane University, Beni Mellal, Morocco</nlm:aff>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PMC</idno>
<idno type="pmid">26217753</idno>
<idno type="pmc">4510372</idno>
<idno type="url">http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4510372</idno>
<idno type="RBID">PMC:4510372</idno>
<idno type="doi">10.1016/j.dib.2015.04.008</idno>
<date when="2015">2015</date>
<idno type="wicri:Area/Pmc/Corpus">000128</idno>
<idno type="wicri:explorRef" wicri:stream="Pmc" wicri:step="Corpus" wicri:corpus="PMC">000128</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a" type="main">Data set for Tifinagh handwriting character recognition</title>
<author><name sortKey="Bencharef, Omar" sort="Bencharef, Omar" uniqKey="Bencharef O" first="Omar" last="Bencharef">Omar Bencharef</name>
<affiliation><nlm:aff id="aff0005">Higher School of Technology-Essaouira, Cadi Ayyad University, Marrakech, Morocco</nlm:aff>
</affiliation>
</author>
<author><name sortKey="Chihab, Younes" sort="Chihab, Younes" uniqKey="Chihab Y" first="Younes" last="Chihab">Younes Chihab</name>
<affiliation><nlm:aff id="aff0010">FP Safi, Cadi Ayyad University, Marrakech, Morocco</nlm:aff>
</affiliation>
</author>
<author><name sortKey="Mousaid, Nouredine" sort="Mousaid, Nouredine" uniqKey="Mousaid N" first="Nouredine" last="Mousaid">Nouredine Mousaid</name>
<affiliation><nlm:aff id="aff0005">Higher School of Technology-Essaouira, Cadi Ayyad University, Marrakech, Morocco</nlm:aff>
</affiliation>
</author>
<author><name sortKey="Oujaoura, Mustapha" sort="Oujaoura, Mustapha" uniqKey="Oujaoura M" first="Mustapha" last="Oujaoura">Mustapha Oujaoura</name>
<affiliation><nlm:aff id="aff0015">Faculty of Science and Technology, Sultan Moulay Slimane University, Beni Mellal, Morocco</nlm:aff>
</affiliation>
</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 Tifinagh alphabet-IRCAM is the official alphabet of the Amazigh language widely used in North Africa <xref rid="bib1" ref-type="bibr">[1]</xref>
. It includes thirty-one basic letter and two letters each composed of a base letter followed by the sign of labialization. Normalized only in 2003 (Unicode) <xref rid="bib2" ref-type="bibr">[2]</xref>
, ICRAM-Tifinagh is a young character repertoire. Which needs more work on all levels. In this context we propose a data set for handwritten Tifinagh characters composed of 1376 image; 43 Image For Each character. The dataset can be used to train a Tifinagh character recognition system, or to extract the meaning characteristics of each character.</p>
</div>
</front>
<back><div1 type="bibliography"><listBibl><biblStruct><analytic><author><name sortKey="Sadiqi, Fatima" uniqKey="Sadiqi F">Fatima Sadiqi</name>
</author>
</analytic>
</biblStruct>
<biblStruct></biblStruct>
<biblStruct><analytic><author><name sortKey="Bentayebia, K" uniqKey="Bentayebia K">K. Bentayebia</name>
</author>
<author><name sortKey="Abadaa, F" uniqKey="Abadaa F">F. Abadaa</name>
</author>
<author><name sortKey="Ihzmadb, H" uniqKey="Ihzmadb H">H. Ihzmadb</name>
</author>
<author><name sortKey="Amzazia, S" uniqKey="Amzazia S">S. Amzazia</name>
</author>
</analytic>
</biblStruct>
<biblStruct><analytic><author><name sortKey="Katherine, E" uniqKey="Katherine E">E. Katherine</name>
</author>
<author><name sortKey="Hoffman" uniqKey="Hoffman">Hoffman</name>
</author>
</analytic>
</biblStruct>
<biblStruct><analytic><author><name sortKey="Oujaoura, M" uniqKey="Oujaoura M">M. Oujaoura</name>
</author>
<author><name sortKey="Minaoui, B" uniqKey="Minaoui B">B. Minaoui</name>
</author>
<author><name sortKey="Fakir, M" uniqKey="Fakir M">M. Fakir</name>
</author>
<author><name sortKey="Ayachi, R" uniqKey="Ayachi R">R. Ayachi</name>
</author>
<author><name sortKey="Bencharef, O" uniqKey="Bencharef O">O. Bencharef</name>
</author>
</analytic>
</biblStruct>
<biblStruct><analytic><author><name sortKey="Vijayashree, C S" uniqKey="Vijayashree C">C.S. Vijayashree</name>
</author>
<author><name sortKey="Kagawade, Vishwanath C" uniqKey="Kagawade V">Vishwanath C. Kagawade</name>
</author>
<author><name sortKey="Vasudev, T" uniqKey="Vasudev T">T. Vasudev</name>
</author>
</analytic>
</biblStruct>
<biblStruct><analytic><author><name sortKey="Kenji Suzuki A, Isao Horiba A" uniqKey="Kenji Suzuki A I">Isao Horiba,a Kenji Suzuki,a</name>
</author>
<author><name sortKey="Sugieb, Noboru" uniqKey="Sugieb N">Noboru Sugieb</name>
</author>
</analytic>
</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">26217753</article-id>
<article-id pub-id-type="pmc">4510372</article-id>
<article-id pub-id-type="publisher-id">S2352-3409(15)00050-5</article-id>
<article-id pub-id-type="doi">10.1016/j.dib.2015.04.008</article-id>
<article-categories><subj-group subj-group-type="heading"><subject>Data Article</subject>
</subj-group>
</article-categories>
<title-group><article-title>Data set for Tifinagh handwriting character recognition</article-title>
</title-group>
<contrib-group><contrib contrib-type="author"><name><surname>Bencharef</surname>
<given-names>Omar</given-names>
</name>
<email>o.bencharef@uca.ma</email>
<xref rid="aff0005" ref-type="aff">a</xref>
<xref rid="cor1" ref-type="corresp">⁎</xref>
</contrib>
<contrib contrib-type="author"><name><surname>Chihab</surname>
<given-names>Younes</given-names>
</name>
<xref rid="aff0010" ref-type="aff">b</xref>
</contrib>
<contrib contrib-type="author"><name><surname>Mousaid</surname>
<given-names>Nouredine</given-names>
</name>
<xref rid="aff0005" ref-type="aff">a</xref>
</contrib>
<contrib contrib-type="author"><name><surname>Oujaoura</surname>
<given-names>Mustapha</given-names>
</name>
<xref rid="aff0015" ref-type="aff">c</xref>
</contrib>
</contrib-group>
<aff id="aff0005"><label>a</label>
Higher School of Technology-Essaouira, Cadi Ayyad University, Marrakech, Morocco</aff>
<aff id="aff0010"><label>b</label>
FP Safi, Cadi Ayyad University, Marrakech, Morocco</aff>
<aff id="aff0015"><label>c</label>
Faculty of Science and Technology, Sultan Moulay Slimane University, Beni Mellal, Morocco</aff>
<author-notes><corresp id="cor1"><label>⁎</label>
Corresponding author. <email>o.bencharef@uca.ma</email>
</corresp>
</author-notes>
<pub-date pub-type="pmc-release"><day>23</day>
<month>4</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>23</day>
<month>4</month>
<year>2015</year>
</pub-date>
<volume>4</volume>
<fpage>11</fpage>
<lpage>13</lpage>
<history><date date-type="received"><day>19</day>
<month>1</month>
<year>2015</year>
</date>
<date date-type="rev-recd"><day>7</day>
<month>4</month>
<year>2015</year>
</date>
<date date-type="accepted"><day>14</day>
<month>4</month>
<year>2015</year>
</date>
</history>
<permissions><copyright-statement>© 2015 The Authors</copyright-statement>
<copyright-year>2015</copyright-year>
</permissions>
<abstract><p>The Tifinagh alphabet-IRCAM is the official alphabet of the Amazigh language widely used in North Africa <xref rid="bib1" ref-type="bibr">[1]</xref>
. It includes thirty-one basic letter and two letters each composed of a base letter followed by the sign of labialization. Normalized only in 2003 (Unicode) <xref rid="bib2" ref-type="bibr">[2]</xref>
, ICRAM-Tifinagh is a young character repertoire. Which needs more work on all levels. In this context we propose a data set for handwritten Tifinagh characters composed of 1376 image; 43 Image For Each character. The dataset can be used to train a Tifinagh character recognition system, or to extract the meaning characteristics of each character.</p>
</abstract>
</article-meta>
</front>
<body><sec id="s0005"><label>1</label>
<title>Specifications table</title>
<p><table-wrap id="t0005" position="float"><table frame="hsides" rules="groups"><tbody><tr><td>Subject area</td>
<td>Computer science</td>
</tr>
<tr><td colspan="2"><hr></hr>
</td>
</tr>
<tr><td>More specific subject area</td>
<td>Image processing, character recognition</td>
</tr>
<tr><td>Type of data</td>
<td>Image</td>
</tr>
<tr><td>How data was acquired</td>
<td>Hand writing and scanner</td>
</tr>
<tr><td>Data format</td>
<td>Jpg image</td>
</tr>
<tr><td>Experimental factors</td>
<td>We ask 30 students to write in each cell of a table all Tifinagh characters, we use an Epson 10000XL to data scan, and we add 13 more features to take on consideration horizontal and vertical inclination</td>
</tr>
<tr><td>Experimental features</td>
<td>1376 Image with a size of 30⁎30px (43 images/character)</td>
</tr>
<tr><td>Data source location</td>
<td>Essaouira, Morocco</td>
</tr>
<tr><td>Data accessibility</td>
<td>Within this article</td>
</tr>
</tbody>
</table>
</table-wrap>
</p>
</sec>
<sec id="s0010"><label>2</label>
<title>Value of the data</title>
<p><list list-type="simple"><list-item id="u0005"><label>•</label>
<p>The Amazigh language is considered as official language only in 2003. Therefore, The integration of the Tifinagh alphabet in new information technologies and communication (ICT) and engage in research in this field has become a major necessity <xref rid="bib1 bib2" ref-type="bibr">[1,2]</xref>
.</p>
</list-item>
<list-item id="u0010"><label>•</label>
<p>The Amazigh language is spoken by about 30 million people in North Africa (the oasis of Siwa in Egypt, Morocco through Libya, Tunisia, Algeria, Niger, Mali, Burkina Faso and Mauritania) <xref rid="bib3 bib4" ref-type="bibr">[3,4]</xref>
.</p>
</list-item>
<list-item id="u0015"><label>•</label>
<p>Due to the diversity of hand writing characters, there are two big approaches in this field and both need a dataset to be executed: the first one is based on complex classifiers like Artificial Neural Network or Support Vector Machine; those classifiers need a dataset to be trained to classify characters<xref rid="bib5" ref-type="bibr">[5]</xref>
. The other approaches also need a dataset this time to find a normalization of each character.</p>
</list-item>
<list-item id="u0020"><label>•</label>
<p>The data set is very useful to train classification system for Tifinagh hand writing, that remain an active area of research.</p>
</list-item>
<list-item id="u0025"><label>•</label>
<p>The dataset is the first free and on line dataset for handwriting Tifinagh character without formalities.</p>
</list-item>
</list>
</p>
</sec>
<sec id="s0015"><label>3</label>
<title>Experimental design, materials and methods</title>
<p>We ask 30 people (17 male and 13 female) to write the 32 Tifinagh (<xref rid="f0005" ref-type="fig">Fig. 1</xref>
) characters on one page, and we add 13 more features to take on consideration horizontal and vertical inclination. The pages where scanned using the Epson 10000XL.</p>
<p>The extraction steps were:<list list-type="simple"><list-item id="u0030"><label>•</label>
<p>We use the horizontal histogram to correct the inclination of every page <xref rid="bib6" ref-type="bibr">[6]</xref>
.</p>
</list-item>
<list-item id="u0035"><label>•</label>
<p>Using connected components algorithm we detect the center of each character <xref rid="bib7" ref-type="bibr">[7]</xref>
.</p>
</list-item>
<list-item id="u0040"><label>•</label>
<p>We extract 31 sub-images of 30×30px that contain the characters (<xref rid="f0010" ref-type="fig">Fig. 2</xref>
).</p>
</list-item>
<list-item id="u0045"><label>•</label>
<p>The sub-image are named using Latin character mentioned in <xref rid="f0005" ref-type="fig">Fig. 1</xref>
for each character followed by number from 1 to 30( a1,a2…a43 ). For character with sub point we use a double character (hh or zz). For epsilon we use a double A(aa1,aa2…aa43).</p>
</list-item>
</list>
</p>
<p>To automatically explore the dataset or to extract features from the whole dataset we propose the following Matlab code:<table-wrap id="t0010" position="float"><table frame="hsides" rules="groups"><tbody><tr><td>function x=base_generation()</td>
</tr>
<tr><td>//Read all jpg image from folder ‘data_set’</td>
</tr>
<tr><td>fileFolder = fullfile(‘data_set’);</td>
</tr>
<tr><td>dirOutput = dir(fullfile(fileFolder,’⁎.jpg’))</td>
</tr>
<tr><td>fileNames = {dirOutput.name}׳</td>
</tr>
<tr><td>numFrames = numel(fileNames)</td>
</tr>
<tr><td>cd ‘data_set׳</td>
</tr>
<tr><td>p = imread(fileNames{2});</td>
</tr>
<tr><td>//We read and converts to gray level the first image then we call the //feature extraction process</td>
</tr>
<tr><td>d=imread(p);</td>
</tr>
<tr><td>d=double(d)/255;</td>
</tr>
<tr><td>y=rgb2gray(d);</td>
</tr>
<tr><td>t =zmoment(y,11); // Call the feature extraction</td>
</tr>
<tr><td>b=t; //we add the ‘t’ to the data matrix</td>
</tr>
<tr><td>// We repeat the same treatment for the rest of the data set</td>
</tr>
<tr><td>for i=2:1240</td>
</tr>
<tr><td>p=m{i};</td>
</tr>
<tr><td>d=imread(p);</td>
</tr>
<tr><td>d=double(d)/255;</td>
</tr>
<tr><td>y=rgb2gray(d);</td>
</tr>
<tr><td><bold>t=zmoment(y,11);</bold>
// Call the feature extraction function(Zernike for // example)</td>
</tr>
<tr><td>b=[b;t];</td>
</tr>
<tr><td>End</td>
</tr>
<tr><td>x=b</td>
</tr>
</tbody>
</table>
</table-wrap>
</p>
</sec>
</body>
<back><ref-list><title>References</title>
<ref id="bib1"><label>1</label>
<element-citation publication-type="book" id="sbref1"><person-group person-group-type="author"><name><surname>Sadiqi</surname>
<given-names>Fatima</given-names>
</name>
</person-group>
<chapter-title>The Teatchin of Tifinagh (Berber) in Morocco, Handbook of Language and Ethnic Identity</chapter-title>
<series>The Success-Failure Continuum in Language and Ethnic Identity Efforts</series>
<volume>vol. 2</volume>
<year>2011</year>
<publisher-name>Oxford University Press</publisher-name>
<fpage>33</fpage>
<lpage>44</lpage>
</element-citation>
</ref>
<ref id="bib2"><label>2</label>
<mixed-citation publication-type="other" id="othref0005">Institut Royal de la Culture Amazighe(IRCAM). Proposition de codification des tifinaghes, Rabat, Morocco, 2003a.</mixed-citation>
</ref>
<ref id="bib3"><label>3</label>
<element-citation publication-type="book" id="sbref2"><person-group person-group-type="author"><name><surname>Bentayebia</surname>
<given-names>K.</given-names>
</name>
<name><surname>Abadaa</surname>
<given-names>F.</given-names>
</name>
<name><surname>Ihzmadb</surname>
<given-names>H.</given-names>
</name>
<name><surname>Amzazia</surname>
<given-names>S.</given-names>
</name>
</person-group>
<chapter-title>Genetic ancestry of a Moroccan population as inferred from autosomal STRs</chapter-title>
<volume>vol. 2</volume>
<year>2014</year>
<publisher-name>Elsevier Meta Gene</publisher-name>
<fpage>427</fpage>
<lpage>438</lpage>
</element-citation>
</ref>
<ref id="bib4"><label>4</label>
<element-citation publication-type="book" id="sbref3"><person-group person-group-type="author"><name><surname>Katherine</surname>
<given-names>E.</given-names>
</name>
<name><surname>Hoffman</surname>
</name>
</person-group>
<chapter-title>Berber Language Ideologies, Maintenance, and Contraction: Gendered Variation in the Indigenous Margins of Morocco</chapter-title>
<volume>vol. 26</volume>
<year>2006</year>
<publisher-name>Elsevier—Language & Communication</publisher-name>
<fpage>144</fpage>
<lpage>167</lpage>
</element-citation>
</ref>
<ref id="bib5"><label>5</label>
<element-citation publication-type="journal" id="sbref4"><person-group person-group-type="author"><name><surname>Oujaoura</surname>
<given-names>M.</given-names>
</name>
<name><surname>Minaoui</surname>
<given-names>B.</given-names>
</name>
<name><surname>Fakir</surname>
<given-names>M.</given-names>
</name>
<name><surname>Ayachi</surname>
<given-names>R.</given-names>
</name>
<name><surname>Bencharef</surname>
<given-names>O.</given-names>
</name>
</person-group>
<article-title>Article: recognition of isolated printed Tifinagh characters</article-title>
<source>Int. J. Comput. Appl.</source>
<volume>85</volume>
<issue>1</issue>
<year>2014</year>
<comment>1-13, January</comment>
</element-citation>
</ref>
<ref id="bib6"><label>6</label>
<element-citation publication-type="journal" id="sbref5"><person-group person-group-type="author"><name><surname>Vijayashree</surname>
<given-names>C.S.</given-names>
</name>
<name><surname>Kagawade</surname>
<given-names>Vishwanath C.</given-names>
</name>
<name><surname>Vasudev</surname>
<given-names>T.</given-names>
</name>
</person-group>
<article-title>Article: estimation of Tilt in characters and correction for better readability by OCR systems</article-title>
<source>Int. J. Comput. Appl.</source>
<volume>90</volume>
<issue>13</issue>
<year>2014</year>
<comment>1-7, March</comment>
</element-citation>
</ref>
<ref id="bib7"><label>7</label>
<element-citation publication-type="journal" id="sbref6"><person-group person-group-type="author"><name><surname>Kenji Suzuki,a</surname>
<given-names>Isao Horiba,a</given-names>
</name>
<name><surname>Sugieb</surname>
<given-names>Noboru</given-names>
</name>
</person-group>
<article-title>Linear-time connected-component labeling based on sequential local operations</article-title>
<source>Comput. Vision Image Understanding</source>
<volume>89</volume>
<year>2003</year>
<fpage>1</fpage>
<lpage>23</lpage>
</element-citation>
</ref>
</ref-list>
<sec sec-type="supplementary-material" id="s0025"><title>Supplementary materials</title>
<p><supplementary-material content-type="local-data" id="ec0005"><caption><p>Supplementary data</p>
</caption>
<media xlink:href="mmc1.zip"></media>
</supplementary-material>
</p>
</sec>
<fn-group><fn id="s0020" fn-type="supplementary-material"><label>Appendix A</label>
<p>Supplementary data associated with this article can be found in the online version at <ext-link ext-link-type="uri" xlink:href="http://dx.doi.org/10.1016/j.dib.2015.04.008" id="ir0005">doi:10.1016/j.dib.2015.04.008</ext-link>
.</p>
</fn>
</fn-group>
</back>
<floats-group><fig id="f0005"><label>Fig. 1</label>
<caption><p>Elementary IRCAM Tifinagh characters.</p>
</caption>
<graphic xlink:href="gr1"></graphic>
</fig>
<fig id="f0010"><label>Fig. 2</label>
<caption><p>Example of handwriting Tifinagh character from the proposed data base.</p>
</caption>
<graphic xlink:href="gr2"></graphic>
</fig>
</floats-group>
</pmc>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Linguistique/explor/TamazightV2/Data/Pmc/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000128 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Pmc/Corpus/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= Corpus |type= RBID |clé= |texte= }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |