<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-04710881</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-02T07:05:35+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Multi-label classification with deep learning techniques applied to the Bscan images of radar GPR</title>
            <title xml:lang="fr">Classification multi-label avec des techniques d'apprentissage profond appliquées aux images Bscan du radar GPR</title>
            <author role="aut">
              <persName>
                <forename type="first">Soukayna</forename>
                <surname>El Karakhi</surname>
              </persName>
              <idno type="halauthorid">3038405-0</idno>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Alain</forename>
                <surname>Reineix</surname>
              </persName>
              <email type="md5">cbb6040ede178251b6c5d70f437c3fd7</email>
              <email type="domain">xlim.fr</email>
              <idno type="idhal" notation="string">alain-reineix</idno>
              <idno type="idhal" notation="numeric">175041</idno>
              <idno type="halauthorid" notation="string">34702-175041</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-9439-6258</idno>
              <idno type="IDREF">https://www.idref.fr/031544274</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=i1DVxbQAAAAJ</idno>
              <idno type="VIAF">https://viaf.org/viaf/64065891</idno>
              <idno type="ISNI">http://isni.org/isni/0000000374419552</idno>
              <affiliation ref="#struct-1192745"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Christophe</forename>
                <surname>Guiffaut</surname>
              </persName>
              <email type="md5">0581075428e8f92724771912a68a653c</email>
              <email type="domain">xlim.fr</email>
              <idno type="idhal" notation="string">christophe-guiffaut</idno>
              <idno type="idhal" notation="numeric">1219</idno>
              <idno type="halauthorid" notation="string">14466-1219</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-7550-9966</idno>
              <idno type="IDREF">https://www.idref.fr/195280237</idno>
              <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=CI_65R4AAAAJ</idno>
              <affiliation ref="#struct-1192745"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Alain</forename>
                <surname>Reineix</surname>
              </persName>
              <email type="md5">cbb6040ede178251b6c5d70f437c3fd7</email>
              <email type="domain">xlim.fr</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2024-09-26 15:44:04</date>
              <date type="whenModified">2025-07-01 15:50:02</date>
              <date type="whenReleased">2024-10-01 15:37:08</date>
              <date type="whenProduced">2024-09-05</date>
              <date type="whenEndEmbargoed">2024-09-26</date>
              <ref type="file" target="https://unilim.hal.science/hal-04710881v1/document">
                <date notBefore="2024-09-26"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://unilim.hal.science/hal-04710881v1/file/Compte_rendu_Physique_ABOUZOUHOUR_Soukayna_Multilabel_deep_learning_technqiues.pdf" id="file-4710881-4097936">
                <date notBefore="2024-09-26"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="162060">
                <persName>
                  <forename>Alain</forename>
                  <surname>Reineix</surname>
                </persName>
                <email type="md5">cbb6040ede178251b6c5d70f437c3fd7</email>
                <email type="domain">xlim.fr</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-04710881</idno>
            <idno type="halUri">https://unilim.hal.science/hal-04710881</idno>
            <idno type="halBibtex">elkarakhi:hal-04710881</idno>
            <idno type="halRefHtml">&lt;i&gt;Comptes Rendus. Physique&lt;/i&gt;, 2024, 25 (S1), pp.1-16. &lt;a target="_blank" href="https://dx.doi.org/10.5802/crphys.193"&gt;&amp;#x27E8;10.5802/crphys.193&amp;#x27E9;&lt;/a&gt;</idno>
            <idno type="halRef">Comptes Rendus. Physique, 2024, 25 (S1), pp.1-16. &amp;#x27E8;10.5802/crphys.193&amp;#x27E9;</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal<ref corresp="#file-4710881-4097936"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt>
            <idno type="stamp" n="UNILIM">Université de Limoges</idno>
            <idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno>
            <idno type="stamp" n="XLIM" corresp="UNILIM">XLIM</idno>
            <idno type="stamp" n="XLIM-SRF" corresp="XLIM">Systèmes RF</idno>
          </seriesStmt>
          <notesStmt>
            <note type="audience" n="2">International</note>
            <note type="popular" n="0">No</note>
            <note type="peer" n="1">Yes</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Multi-label classification with deep learning techniques applied to the Bscan images of radar GPR</title>
                <title xml:lang="fr">Classification multi-label avec des techniques d'apprentissage profond appliquées aux images Bscan du radar GPR</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Soukayna</forename>
                    <surname>El Karakhi</surname>
                  </persName>
                  <idno type="halauthorid">3038405-0</idno>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Alain</forename>
                    <surname>Reineix</surname>
                  </persName>
                  <email type="md5">cbb6040ede178251b6c5d70f437c3fd7</email>
                  <email type="domain">xlim.fr</email>
                  <idno type="idhal" notation="string">alain-reineix</idno>
                  <idno type="idhal" notation="numeric">175041</idno>
                  <idno type="halauthorid" notation="string">34702-175041</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-9439-6258</idno>
                  <idno type="IDREF">https://www.idref.fr/031544274</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=i1DVxbQAAAAJ</idno>
                  <idno type="VIAF">https://viaf.org/viaf/64065891</idno>
                  <idno type="ISNI">http://isni.org/isni/0000000374419552</idno>
                  <affiliation ref="#struct-1192745"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Christophe</forename>
                    <surname>Guiffaut</surname>
                  </persName>
                  <email type="md5">0581075428e8f92724771912a68a653c</email>
                  <email type="domain">xlim.fr</email>
                  <idno type="idhal" notation="string">christophe-guiffaut</idno>
                  <idno type="idhal" notation="numeric">1219</idno>
                  <idno type="halauthorid" notation="string">14466-1219</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-7550-9966</idno>
                  <idno type="IDREF">https://www.idref.fr/195280237</idno>
                  <idno type="GOOGLE SCHOLAR">https://scholar.google.fr/citations?user=CI_65R4AAAAJ</idno>
                  <affiliation ref="#struct-1192745"/>
                </author>
              </analytic>
              <monogr>
                <idno type="halJournalId" status="VALID">11993</idno>
                <idno type="issn">1631-0705</idno>
                <idno type="eissn">1878-1535</idno>
                <title level="j">Comptes Rendus. Physique</title>
                <imprint>
                  <publisher>Académie des sciences (Paris)</publisher>
                  <biblScope unit="volume">25</biblScope>
                  <biblScope unit="issue">S1</biblScope>
                  <biblScope unit="pp">1-16</biblScope>
                  <date type="datePub">2024-09-05</date>
                </imprint>
              </monogr>
              <idno type="doi">10.5802/crphys.193</idno>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">Image processing</term>
                <term xml:lang="en">Detection of Buried objects</term>
                <term xml:lang="en">Deep learning</term>
                <term xml:lang="en">Ground Penetrating Radar</term>
                <term xml:lang="en">Ground Penetrating Radar Image processing Detection of Buried objects Deep learning</term>
              </keywords>
              <classCode scheme="halDomain" n="spi">Engineering Sciences [physics]</classCode>
              <classCode scheme="halTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halOldTypology" n="ART">Journal articles</classCode>
              <classCode scheme="halTreeTypology" n="ART">Journal articles</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>The ground penetrating radars (GPR) are now widely used for the detection of buried objects in areas such as: geology, archaeology and civil engineering. It has the advantage of allowing detection by a non-destructive technique. The principle for time domain GPR consists in emitting electromagnetic pulses in the ground, these one are then diffracted by the targets to be detected. A single GPR signal trace captured at a position of the radar is a 1D signal called Ascan. A set of Ascan radar waveforms captured at a certain number of different consecutive positions along a particular direction will form a 2D image called B-scan. They show response shapes of hyperbolic type and their analysis give many characteristics. For example, in the case of buried pipes, a specific processing allows to find their diameter, their nature as well as the electrical characteristics of the ground. However, these approaches often require complex post-processing of the Bscan, which can be time-consuming and therefore makes it difficult to perform realtime characterization at the expense of such methods. With the emergence of deep neural networks and with a learning phase on a large number of Bscan, it becomes possible to extract almost instantaneously the characteristics of GPR radar data. In this study, a multi-label classification (MLC) model based on transfer learning and data augmentation has been developed to generate multiple information elements on the same image and to realize classification. Three deep learning models: VGG-16, ResNet-50 and adapted CNN were used as pre-trained models for transfer learning. The networks were trained on a synthetic dataset created in this study and evaluated on a set of performance metrics.&lt;/p&gt;&lt;p&gt;Les radars à pénétration de sol (GPR) sont aujourd'hui largement utilisés pour la détection d'objets enterrés dans des domaines tels que la géologie, l'archéologie et le génie civil. Il présente l'avantage de permettre une détection par une technique non destructive. Le principe du GPR dans le domaine temporel consiste à émettre des impulsions électromagnétiques dans le sol, celles-ci étant ensuite diffractées par les cibles à détecter. Une seule trace de signal GPR capturée à une position du radar est un signal 1D appelé Ascan. Un ensemble de formes d'ondes radar Ascan capturées à un certain nombre de positions consécutives différentes le long d'une direction particulière formera une image 2D appelée B-scan dans le cas d'un déplacement rectiligne. Elles montrent des formes de réponse de type hyperbolique et leur analyse donne de nombreuses caractéristiques. Par exemple, dans le cas de canalisations enterrées, un traitement spécifique permet de connaître leur diamètre, leur nature ainsi que les caractéristiques électriques du sol. Cependant, ces approches nécessitent souvent un post-traitement complexe du Bscan, ce qui peut être chronophage et rend donc difficile la caractérisation en temps réel au détriment de ces méthodes. Avec l'émergence des réseaux neuronaux profonds et avec une phase d'apprentissage sur un grand nombre de Bscan, il devient possible d'extraire presque instantanément les caractéristiques des données radar GPR. Dans cette étude, un modèle de classification multi-label (MLC) basé sur l'apprentissage par transfert et l'augmentation des données a été développé pour générer des éléments d'information multiples sur la même image et réaliser la classification. Trois modèles d'apprentissage profond : VGG-16, ResNet-50 et CNN adapté ont été utilisés comme modèles pré-entraînés pour l'apprentissage par transfert. Les réseaux ont été formés sur un ensemble de données synthétiques créé dans cette étude et évalués sur un ensemble de mesures de performance.&lt;/p&gt;&lt;/div&gt;</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="researchteam" xml:id="struct-1192745" status="VALID">
          <idno type="IdRef">128007052</idno>
          <idno type="RNSR">201622925D</idno>
          <idno type="ROR">https://ror.org/00f7srh09</idno>
          <idno type="Wikidata">Q30261539</idno>
          <orgName>Systèmes RF</orgName>
          <orgName type="acronym">XLIM-SRF</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <addrLine>123 avenue Albert Thomas 87060 Limoges Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.xlim.fr/</ref>
          </desc>
          <listRelation>
            <relation name="SRF" active="#struct-1192734" type="direct"/>
            <relation active="#struct-5928" type="indirect"/>
            <relation name="UMR7252" active="#struct-441569" type="indirect"/>
          </listRelation>
        </org>
        <org type="laboratory" xml:id="struct-1192734" status="VALID">
          <idno type="IdRef">128007052</idno>
          <idno type="ISNI">0000000405977726</idno>
          <idno type="RNSR">201220195D</idno>
          <idno type="ROR">https://ror.org/00f7srh09</idno>
          <idno type="Wikidata">https://www.wikidata.org/wiki/Q30261539</idno>
          <orgName>XLIM</orgName>
          <orgName type="acronym">XLIM</orgName>
          <date type="start">2022-01-01</date>
          <desc>
            <address>
              <addrLine>123 Avenue Albert Thomas 87060 Limoges Cedex</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.xlim.fr</ref>
          </desc>
          <listRelation>
            <relation active="#struct-5928" type="direct"/>
            <relation name="UMR7252" active="#struct-441569" type="direct"/>
          </listRelation>
        </org>
        <org type="institution" xml:id="struct-5928" status="VALID">
          <idno type="IdRef">026403315</idno>
          <idno type="ISNI">0000000121654861</idno>
          <idno type="ROR">https://ror.org/02cp04407</idno>
          <orgName>Université de Limoges</orgName>
          <orgName type="acronym">UNILIM</orgName>
          <date type="start">1968-10-01</date>
          <desc>
            <address>
              <addrLine>33 rue François Mitterrand BP23204 87032 Limoges</addrLine>
              <country key="FR"/>
            </address>
            <ref type="url">http://www.unilim.fr</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-441569" status="VALID">
          <idno type="IdRef">02636817X</idno>
          <idno type="ISNI">0000000122597504</idno>
          <idno type="ROR">https://ror.org/02feahw73</idno>
          <orgName>Centre National de la Recherche Scientifique</orgName>
          <orgName type="acronym">CNRS</orgName>
          <date type="start">1939-10-19</date>
          <desc>
            <address>
              <country key="FR"/>
            </address>
            <ref type="url">https://www.cnrs.fr/</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>