<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//TaxonX//DTD Taxonomic Treatment Publishing DTD v0 20100105//EN" "../../nlm/tax-treatment-NS0.dtd">
<article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:tp="http://www.plazi.org/taxpub" article-type="research-article">
  <front>
    <journal-meta>
      <journal-id journal-id-type="publisher-id">63</journal-id>
      <journal-id journal-id-type="index">urn:lsid:arphahub.com:pub:0E0032F4-55AE-5263-8B3C-F4DD637C30C2</journal-id>
      <journal-title-group>
        <journal-title xml:lang="en">Biodiversity Information Science and Standards</journal-title>
        <abbrev-journal-title xml:lang="en">BISS</abbrev-journal-title>
      </journal-title-group>
      <issn pub-type="epub">2535-0897</issn>
      <publisher>
        <publisher-name>Pensoft Publishers</publisher-name>
      </publisher>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="doi">10.3897/biss.8.138060</article-id>
      <article-id pub-id-type="publisher-id">138060</article-id>
      <article-id pub-id-type="manuscript">25501</article-id>
      <article-categories>
        <subj-group subj-group-type="heading">
          <subject>Conference Abstract</subject>
        </subj-group>
        <subj-group subj-group-type="conference-part">
          <subject>SYM20 - Herbarium Procedures and Techniques: Sharing best practice from across the globe</subject>
        </subj-group>
        <subj-group subj-group-type="scientific_subject">
          <subject>Databases</subject>
          <subject>Natural History</subject>
          <subject>Systematics</subject>
        </subj-group>
        <subj-group subj-group-type="geographical_area">
          <subject>Far East</subject>
        </subj-group>
      </article-categories>
      <title-group>
        <article-title>Development of an Automated Label Data Entry System from Herbarium Specimen Images at Hyogo Herbarium (HYO)</article-title>
      </title-group>
      <contrib-group content-type="authors">
        <contrib contrib-type="author" corresp="yes">
          <name name-style="western">
            <surname>Takano</surname>
            <given-names>Atsuko</given-names>
          </name>
          <email xlink:type="simple">takano@hitohaku.jp</email>
          <uri content-type="orcid">https://orcid.org/0000-0002-8345-5080</uri>
          <xref ref-type="aff" rid="A1">1</xref>
          <xref ref-type="aff" rid="A2">2</xref>
        </contrib>
        <contrib contrib-type="author" corresp="no">
          <name name-style="western">
            <surname>Horiuchi</surname>
            <given-names>Yasuhiko</given-names>
          </name>
          <xref ref-type="aff" rid="A3">3</xref>
        </contrib>
        <contrib contrib-type="author" corresp="no">
          <name name-style="western">
            <surname>Konagai</surname>
            <given-names>Hajime</given-names>
          </name>
          <xref ref-type="aff" rid="A4">4</xref>
          <role content-type="http://credit.niso.org/contributor-roles/methodology/">Methodology</role>
        </contrib>
        <contrib contrib-type="author" corresp="no">
          <name name-style="western">
            <surname>Lee</surname>
            <given-names>Chung-Kun</given-names>
          </name>
          <xref ref-type="aff" rid="A5">5</xref>
          <xref ref-type="aff" rid="A6">6</xref>
        </contrib>
        <contrib contrib-type="author" corresp="no">
          <name name-style="western">
            <surname>Mitsuhashi</surname>
            <given-names>Hiromune</given-names>
          </name>
          <xref ref-type="aff" rid="A7">7</xref>
          <role content-type="http://credit.niso.org/contributor-roles/methodology/">Methodology</role>
        </contrib>
      </contrib-group>
      <aff id="A1">
        <label>1</label>
        <addr-line content-type="verbatim">University of Hyogo, Sanda, Japan</addr-line>
        <institution>University of Hyogo</institution>
        <addr-line content-type="city">Sanda</addr-line>
        <country>Japan</country>
      </aff>
      <aff id="A2">
        <label>2</label>
        <addr-line content-type="verbatim">Museum of Nature and Human Activities, Hyogo, Sanda, Japan</addr-line>
        <institution>Museum of Nature and Human Activities, Hyogo</institution>
        <addr-line content-type="city">Sanda</addr-line>
        <country>Japan</country>
      </aff>
      <aff id="A3">
        <label>3</label>
        <addr-line content-type="verbatim">The NPO Field, Takatsuki, Japan</addr-line>
        <institution>The NPO Field</institution>
        <addr-line content-type="city">Takatsuki</addr-line>
        <country>Japan</country>
      </aff>
      <aff id="A4">
        <label>4</label>
        <addr-line content-type="verbatim">Functiontales, Kyoto, Japan</addr-line>
        <institution>Functiontales</institution>
        <addr-line content-type="city">Kyoto</addr-line>
        <country>Japan</country>
      </aff>
      <aff id="A5">
        <label>5</label>
        <addr-line content-type="verbatim">Museum of Nature and Human Activities, Sanda, Japan</addr-line>
        <institution>Museum of Nature and Human Activities</institution>
        <addr-line content-type="city">Sanda</addr-line>
        <country>Japan</country>
      </aff>
      <aff id="A6">
        <label>6</label>
        <addr-line content-type="verbatim">University of Hyogo, Hyogo, Japan</addr-line>
        <institution>University of Hyogo</institution>
        <addr-line content-type="city">Hyogo</addr-line>
        <country>Japan</country>
      </aff>
      <aff id="A7">
        <label>7</label>
        <addr-line content-type="verbatim">University of Hyogo, Museum of Nature and Human Activities, Hyogo, Sanda, Japan</addr-line>
        <institution>University of Hyogo, Museum of Nature and Human Activities, Hyogo</institution>
        <addr-line content-type="city">Sanda</addr-line>
        <country>Japan</country>
      </aff>
      <author-notes>
        <fn fn-type="corresp">
          <p>Corresponding author: Atsuko Takano (<email xlink:type="simple">takano@hitohaku.jp</email>).</p>
        </fn>
        <fn fn-type="edited-by">
          <p>Academic editor: </p>
        </fn>
      </author-notes>
      <pub-date pub-type="collection">
        <year>2024</year>
      </pub-date>
      <pub-date pub-type="epub">
        <day>30</day>
        <month>09</month>
        <year>2024</year>
      </pub-date>
      <volume>8</volume>
      <elocation-id>e138060</elocation-id>
      <uri content-type="arpha" xlink:href="http://openbiodiv.net/9F66EB41-D870-539C-97D0-D92EC104FBAE">9F66EB41-D870-539C-97D0-D92EC104FBAE</uri>
      <permissions>
        <copyright-statement>Atsuko Takano, Yasuhiko Horiuchi, Hajime Konagai, Chung-Kun Lee, Hiromune Mitsuhashi</copyright-statement>
        <license license-type="creative-commons-attribution" xlink:href="http://creativecommons.org/licenses/by/4.0/" xlink:type="simple">
          <license-p>This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.</license-p>
        </license>
      </permissions>
      <abstract>
        <label>Abstract</label>
        <p>We would like to introduce our recently developed systems for taking images of herbarium specimens and for the automatic extraction of data from specimen labels at the Herbarium of the Museum of Nature and Human Activities, Hyogo, Japan (HYO).</p>
        <p>Firstly, we designed a low-cost, but high-quality specimen imaging system for non-professional photographers to obtain images rapidly (<xref ref-type="bibr" rid="B12107984">Takano et al. 2019</xref>). Our system uses a mass-produced, mirrorless single-lens reflex (SLR) camera (SONY ILCE6300) with a zoom lens (Samyang Optics SYIO35AF-E35 mm F/2.8). We made a photo stand by ourselves to reduce costs. In addition, we have adopted an LED (light-emitting diode) lighting system with high color rendering. This imaging system has been introduced, with some improvements or adjustments for available space, to various herbaria in Japan (e.g., University of Tokyo (TI), Kyoto University (KYO)), contributing to the digitization of herbarium specimens across Japan.</p>
        <p>Next, we developed a system to extract label information from specimen images. The specimen image was uploaded to <ext-link ext-link-type="uri" xlink:href="https://cloud.google.com/vision/docs/ocr">Google OCR</ext-link> and data were extracted in the form of text. Uploading the whole specimen image decreased the reading accuracy of the software because the plant images behaved as OCR (Optical Character Reader) noise. Therefore, the label part was cut out from the whole specimen image by using D-Lib*<xref ref-type="fn" rid="FN12109812">1</xref> and uploaded to tesseract OCR*<xref ref-type="fn" rid="FN12109813">2</xref> for OCR extraction of the label information (<xref ref-type="bibr" rid="B12107995">Aoki 2019</xref>, <xref ref-type="bibr" rid="B12108003">Takano et al. 2020</xref>). When installing this system for HYO, we designed it as an application accessible externally via the internet, which proved very useful during the coronavirus pandemic: part-time workers checked and conducted label data input from home.</p>
        <p>Finally, we decided to develop a system that would automatically label the text data extracted by OCR and input them into the appropriate cells of the database. Even though the text data could be extracted from specimen images, it needed a human to input them into the database. Therefore, we adopted Named Entity Recognition (NER), a system that extracts named entities such as place names, identifying proper nouns from unstructured text data. It enables information recorded in herbarium specimens to be tagged as named entities. We tried text matching at first, but the result was not satisfactory, so we started to use machine learning instead. We compared three natural language libraries for Japanese: BERT (Bidirectional Encoder Representations from Transformers), Albert (A Lite version of BERT), and SpaCy. Despite BERT and SpaCy returning similarly high f-scores (indicating good performance), we decided to use <ext-link ext-link-type="uri" xlink:href="https://spacy.io/">SpaCy</ext-link> because it runs better on ordinary PCs or servers. With sufficient machine learning after the creation of a text corpus (a specialised dataset) specific to labels on herbarium specimens, we successfully developed the application. The project files are available on GitHub*<xref ref-type="fn" rid="FN12108079">3</xref> (<xref ref-type="bibr" rid="B12108013">Takano et al. 2024</xref>).</p>
        <p>We then examined whether this system could be applied to non-plant specimen images, i.e., fishes or birds, and found that it could efficiently extract data. Therefore, we decided to publicize this system on the cloud server and share it with other natural history museums in Japan*<xref ref-type="fn" rid="FN12108080">4</xref>. Curators can obtain a unique ID and password and upload specimen images from their collection to extract label data. The digitization of natural history collections in Japan has been long behind other countries, and this system will help to accelerate it.</p>
        <p>The system mentioned above is specialized for the natural history collections of Japan, but we believe it is possible to build similar programs in other countries, and we hope our experience will contribute to the mobilization of the world’s natural history collections.</p>
      </abstract>
      <kwd-group>
        <label>Keywords</label>
        <kwd>named entity recognition</kwd>
        <kwd>optical character recognition</kwd>
        <kwd>digitization</kwd>
      </kwd-group>
      <counts>
        <fig-count count="0"/>
        <table-count count="0"/>
        <ref-count count="4"/>
      </counts>
    </article-meta>
    <notes>
      <sec sec-type="Presenting author">
        <title>Presenting author</title>
        <p>Atsuko Takano</p>
      </sec>
      <sec sec-type="Presented at">
        <title>Presented at</title>
        <p>SPNHC-TDWG 2024</p>
      </sec>
    </notes>
  </front>
  
  <back>
    <sec sec-type="Conflicts of interest">
      <title>Conflicts of interest</title>
      <p>No conflict of interest to declare</p>
      <p>Disclaimer: This article is (co-)authored by any of the Editors-in-Chief, Managing Editors or their deputies in this journal.</p>
    </sec>
    <ref-list>
      <title>References</title>
      <ref id="B12107995">
        <element-citation publication-type="thesis">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Aoki</surname>
              <given-names>K.</given-names>
            </name>
          </person-group>
          <year>2019</year>
          <source>Automatic recognition and extraction of specimen labels in digital imaging herbarium specimens. "On the subject of the Shoei Collection"</source>
          <publisher-name>Doshisha University Graduate School of Culture and Information Science.</publisher-name>
          <comment content-type="language">Japanese</comment>
        </element-citation>
      </ref>
      <ref id="B12107984">
        <element-citation publication-type="article">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Takano</surname>
              <given-names>Atsuko</given-names>
            </name>
            <name name-style="western">
              <surname>Horiuchi</surname>
              <given-names>Yasuhiko</given-names>
            </name>
            <name name-style="western">
              <surname>Fujimoto</surname>
              <given-names>Yu</given-names>
            </name>
            <name name-style="western">
              <surname>Aoki</surname>
              <given-names>Kouta</given-names>
            </name>
            <name name-style="western">
              <surname>Mitsuhashi</surname>
              <given-names>Hiromune</given-names>
            </name>
            <name name-style="western">
              <surname>Takahashi</surname>
              <given-names>Akira</given-names>
            </name>
          </person-group>
          <year>2019</year>
          <article-title>Simple but long-lasting: A specimen imaging method applicable for small- and medium-sized herbaria</article-title>
          <source>PhytoKeys</source>
          <volume>118</volume>
          <fpage>1</fpage>
          <lpage>14</lpage>
          <pub-id pub-id-type="doi">10.3897/phytokeys.118.29434</pub-id>
        </element-citation>
      </ref>
      <ref id="B12108003">
        <element-citation publication-type="article">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Takano</surname>
              <given-names>Atsuko</given-names>
            </name>
            <name name-style="western">
              <surname>Horiuchi</surname>
              <given-names>Yasuhiko</given-names>
            </name>
            <name name-style="western">
              <surname>Aoki</surname>
              <given-names>Kota</given-names>
            </name>
            <name name-style="western">
              <surname>Fujimoto</surname>
              <given-names>Yu</given-names>
            </name>
            <name name-style="western">
              <surname>Mitsuhashi</surname>
              <given-names>Hiromune</given-names>
            </name>
          </person-group>
          <year>2020</year>
          <article-title>Developing new methods for digitization of herbarium specimens and electronic data capture adjustable Japanese herbaria.</article-title>
          <source>Jour. Phytogeogr. Taxon</source>
          <volume>68</volume>
          <issue>2</issue>
          <fpage>103</fpage>
          <lpage>119</lpage>
          <comment content-type="language">Japanese</comment>
          <pub-id pub-id-type="doi">10.18942/chiribunrui.0682-05</pub-id>
        </element-citation>
      </ref>
      <ref id="B12108013">
        <element-citation publication-type="article">
          <person-group person-group-type="author">
            <name name-style="western">
              <surname>Takano</surname>
              <given-names>Atsuko</given-names>
            </name>
            <name name-style="western">
              <surname>Cole</surname>
              <given-names>Theodor C. H.</given-names>
            </name>
            <name name-style="western">
              <surname>Konagai</surname>
              <given-names>Hajime</given-names>
            </name>
          </person-group>
          <year>2024</year>
          <article-title>A novel automated label data extraction and data base generation system from herbarium specimen images using OCR and NER</article-title>
          <source>Scientific Reports</source>
          <volume>14</volume>
          <issue>1</issue>
          <pub-id pub-id-type="doi">10.1038/s41598-023-50179-0</pub-id>
        </element-citation>
      </ref>
    </ref-list>
    <fn-group>
      <fn id="FN12109812">
        <label>*1</label>
        <p>
          <ext-link ext-link-type="uri" xlink:href="http://dlib.net/">http://dlib.net/</ext-link>
        </p>
      </fn>
      <fn id="FN12109813">
        <label>*2</label>
        <p>
          <ext-link ext-link-type="uri" xlink:href="https://github.com/tesseract-ocr">https://github.com/tesseract-ocr</ext-link>
        </p>
      </fn>
      <fn id="FN12108079">
        <label>*3</label>
        <p>
          <ext-link ext-link-type="uri" xlink:href="https://github.com/HajimeKonagai/HitohakuA-Lalabel">https://github.com/HajimeKonagai/HitohakuA-Lalabel</ext-link>
        </p>
      </fn>
      <fn id="FN12108080">
        <label>*4</label>
        <p>
          <ext-link ext-link-type="uri" xlink:href="https://innovatemuseum.net/">https://innovatemuseum.net/</ext-link>
        </p>
      </fn>
    </fn-group>
  </back>
</article>
