Loading…

Discrimination of wheel-thrown pottery surface treatment by Deep Learning

The study of pottery surface treatment is essential to understand techniques used by ancient potters, in order to explore the cultural and economic organisation of past societies. Pottery is one of the most abundant materials found in archaeological excavation, yet classification of pottery surface...

Full description

Saved in:
Bibliographic Details
Published in:Archaeological and anthropological sciences 2022-05, Vol.14 (5), Article 85
Main Authors: Wilczek, Josef, Thér, Richard, Monna, Fabrice, Gentil, Christian, Roudet, Céline, Chateau-Smith, Carmela
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c356t-f709fdfdb127fef5511b482cf51fa35c629e3ba814c37541ea7b6c0e9206cf743
cites cdi_FETCH-LOGICAL-c356t-f709fdfdb127fef5511b482cf51fa35c629e3ba814c37541ea7b6c0e9206cf743
container_end_page
container_issue 5
container_start_page
container_title Archaeological and anthropological sciences
container_volume 14
creator Wilczek, Josef
Thér, Richard
Monna, Fabrice
Gentil, Christian
Roudet, Céline
Chateau-Smith, Carmela
description The study of pottery surface treatment is essential to understand techniques used by ancient potters, in order to explore the cultural and economic organisation of past societies. Pottery is one of the most abundant materials found in archaeological excavation, yet classification of pottery surface treatments remains challenging. The goal of this study is to propose a workflow to classify pottery surface treatments automatically, based on the extraction of images depicting surface geometry, calculated from 3D models. These images are then classified by Deep Learning. Three Convolutional Neural Network algorithms (VGG16 and VGG19 transfer learning, and a custom network) are quantitatively evaluated on an experimental dataset of 48 wheel-thrown vessels, created by a professional potter specifically for this study. To demonstrate workflow feasibility, six different surface treatments were applied to each vessel. Results obtained for all three classifiers (accuracy of 93 to 95%) surpass other state-of-the-art quantitative approaches proposed for pottery classification. The workflow is able to take into account the entire surface of the pottery, not only a pre-selected spatially limited area.
doi_str_mv 10.1007/s12520-022-01501-w
format article
fullrecord <record><control><sourceid>proquest_hal_p</sourceid><recordid>TN_cdi_hal_primary_oai_HAL_halshs_03823239v1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2649214804</sourcerecordid><originalsourceid>FETCH-LOGICAL-c356t-f709fdfdb127fef5511b482cf51fa35c629e3ba814c37541ea7b6c0e9206cf743</originalsourceid><addsrcrecordid>eNp9kMtOwzAQRS0EEqXwA6wssSXgR5zHsiqPVorEBtaW446bVG0cbJeof49LUNmxmtHo3KvRQeiWkgdKSP7oKROMJISxhFBBaDKcoQktsiwpRSbOT7vIL9GV95uYIYSmE7R8ar127a7tVGhth63BQwOwTULj7NDh3oYA7oD93hmlAQcHKuygC7g-4CeAHlegXNd262t0YdTWw83vnKKPl-f3-SKp3l6X81mVaC6ykJiclGZlVjVluQEjBKV1WjBtBDWKC52xEnitCppqnouUgsrrTBMoGcm0yVM-Rfdjb6O2so-vK3eQVrVyMatkvPnGS8ILxhkvv2jE70a8d_ZzDz7Ijd27LnKSZWnJaFqQYykbKe2s9w7MqZkSeTQsR8MyGpY_huUQQ3wM-Qh3a3B_1f-kvgEP6n6q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2649214804</pqid></control><display><type>article</type><title>Discrimination of wheel-thrown pottery surface treatment by Deep Learning</title><source>International Bibliography of the Social Sciences (IBSS)</source><source>Springer Nature</source><creator>Wilczek, Josef ; Thér, Richard ; Monna, Fabrice ; Gentil, Christian ; Roudet, Céline ; Chateau-Smith, Carmela</creator><creatorcontrib>Wilczek, Josef ; Thér, Richard ; Monna, Fabrice ; Gentil, Christian ; Roudet, Céline ; Chateau-Smith, Carmela</creatorcontrib><description>The study of pottery surface treatment is essential to understand techniques used by ancient potters, in order to explore the cultural and economic organisation of past societies. Pottery is one of the most abundant materials found in archaeological excavation, yet classification of pottery surface treatments remains challenging. The goal of this study is to propose a workflow to classify pottery surface treatments automatically, based on the extraction of images depicting surface geometry, calculated from 3D models. These images are then classified by Deep Learning. Three Convolutional Neural Network algorithms (VGG16 and VGG19 transfer learning, and a custom network) are quantitatively evaluated on an experimental dataset of 48 wheel-thrown vessels, created by a professional potter specifically for this study. To demonstrate workflow feasibility, six different surface treatments were applied to each vessel. Results obtained for all three classifiers (accuracy of 93 to 95%) surpass other state-of-the-art quantitative approaches proposed for pottery classification. The workflow is able to take into account the entire surface of the pottery, not only a pre-selected spatially limited area.</description><identifier>ISSN: 1866-9557</identifier><identifier>ISSN: 1866-9565</identifier><identifier>EISSN: 1866-9565</identifier><identifier>DOI: 10.1007/s12520-022-01501-w</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Anthropology ; Archaeology ; Archaeology and Prehistory ; Ceramics ; Chemistry/Food Science ; Classification ; Deep learning ; Discrimination ; Earth and Environmental Science ; Earth Sciences ; Excavation ; Extraction ; Feasibility ; Geography ; Geometry ; Humanities and Social Sciences ; Learning ; Life Sciences ; Neural networks ; Original Paper ; Pottery</subject><ispartof>Archaeological and anthropological sciences, 2022-05, Vol.14 (5), Article 85</ispartof><rights>The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022</rights><rights>The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2022.</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c356t-f709fdfdb127fef5511b482cf51fa35c629e3ba814c37541ea7b6c0e9206cf743</citedby><cites>FETCH-LOGICAL-c356t-f709fdfdb127fef5511b482cf51fa35c629e3ba814c37541ea7b6c0e9206cf743</cites><orcidid>0000-0001-8633-5095 ; 0000-0001-7771-2434 ; 0000-0002-0704-081X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,314,780,784,885,12847,27924,27925,33223</link.rule.ids><backlink>$$Uhttps://shs.hal.science/halshs-03823239$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Wilczek, Josef</creatorcontrib><creatorcontrib>Thér, Richard</creatorcontrib><creatorcontrib>Monna, Fabrice</creatorcontrib><creatorcontrib>Gentil, Christian</creatorcontrib><creatorcontrib>Roudet, Céline</creatorcontrib><creatorcontrib>Chateau-Smith, Carmela</creatorcontrib><title>Discrimination of wheel-thrown pottery surface treatment by Deep Learning</title><title>Archaeological and anthropological sciences</title><addtitle>Archaeol Anthropol Sci</addtitle><description>The study of pottery surface treatment is essential to understand techniques used by ancient potters, in order to explore the cultural and economic organisation of past societies. Pottery is one of the most abundant materials found in archaeological excavation, yet classification of pottery surface treatments remains challenging. The goal of this study is to propose a workflow to classify pottery surface treatments automatically, based on the extraction of images depicting surface geometry, calculated from 3D models. These images are then classified by Deep Learning. Three Convolutional Neural Network algorithms (VGG16 and VGG19 transfer learning, and a custom network) are quantitatively evaluated on an experimental dataset of 48 wheel-thrown vessels, created by a professional potter specifically for this study. To demonstrate workflow feasibility, six different surface treatments were applied to each vessel. Results obtained for all three classifiers (accuracy of 93 to 95%) surpass other state-of-the-art quantitative approaches proposed for pottery classification. The workflow is able to take into account the entire surface of the pottery, not only a pre-selected spatially limited area.</description><subject>Anthropology</subject><subject>Archaeology</subject><subject>Archaeology and Prehistory</subject><subject>Ceramics</subject><subject>Chemistry/Food Science</subject><subject>Classification</subject><subject>Deep learning</subject><subject>Discrimination</subject><subject>Earth and Environmental Science</subject><subject>Earth Sciences</subject><subject>Excavation</subject><subject>Extraction</subject><subject>Feasibility</subject><subject>Geography</subject><subject>Geometry</subject><subject>Humanities and Social Sciences</subject><subject>Learning</subject><subject>Life Sciences</subject><subject>Neural networks</subject><subject>Original Paper</subject><subject>Pottery</subject><issn>1866-9557</issn><issn>1866-9565</issn><issn>1866-9565</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>8BJ</sourceid><recordid>eNp9kMtOwzAQRS0EEqXwA6wssSXgR5zHsiqPVorEBtaW446bVG0cbJeof49LUNmxmtHo3KvRQeiWkgdKSP7oKROMJISxhFBBaDKcoQktsiwpRSbOT7vIL9GV95uYIYSmE7R8ar127a7tVGhth63BQwOwTULj7NDh3oYA7oD93hmlAQcHKuygC7g-4CeAHlegXNd262t0YdTWw83vnKKPl-f3-SKp3l6X81mVaC6ykJiclGZlVjVluQEjBKV1WjBtBDWKC52xEnitCppqnouUgsrrTBMoGcm0yVM-Rfdjb6O2so-vK3eQVrVyMatkvPnGS8ILxhkvv2jE70a8d_ZzDz7Ijd27LnKSZWnJaFqQYykbKe2s9w7MqZkSeTQsR8MyGpY_huUQQ3wM-Qh3a3B_1f-kvgEP6n6q</recordid><startdate>20220501</startdate><enddate>20220501</enddate><creator>Wilczek, Josef</creator><creator>Thér, Richard</creator><creator>Monna, Fabrice</creator><creator>Gentil, Christian</creator><creator>Roudet, Céline</creator><creator>Chateau-Smith, Carmela</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><general>Springer</general><scope>AAYXX</scope><scope>CITATION</scope><scope>8BJ</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>BHPHI</scope><scope>BKSAR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FQK</scope><scope>HCIFZ</scope><scope>JBE</scope><scope>PCBAR</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>1XC</scope><scope>BXJBU</scope><orcidid>https://orcid.org/0000-0001-8633-5095</orcidid><orcidid>https://orcid.org/0000-0001-7771-2434</orcidid><orcidid>https://orcid.org/0000-0002-0704-081X</orcidid></search><sort><creationdate>20220501</creationdate><title>Discrimination of wheel-thrown pottery surface treatment by Deep Learning</title><author>Wilczek, Josef ; Thér, Richard ; Monna, Fabrice ; Gentil, Christian ; Roudet, Céline ; Chateau-Smith, Carmela</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c356t-f709fdfdb127fef5511b482cf51fa35c629e3ba814c37541ea7b6c0e9206cf743</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Anthropology</topic><topic>Archaeology</topic><topic>Archaeology and Prehistory</topic><topic>Ceramics</topic><topic>Chemistry/Food Science</topic><topic>Classification</topic><topic>Deep learning</topic><topic>Discrimination</topic><topic>Earth and Environmental Science</topic><topic>Earth Sciences</topic><topic>Excavation</topic><topic>Extraction</topic><topic>Feasibility</topic><topic>Geography</topic><topic>Geometry</topic><topic>Humanities and Social Sciences</topic><topic>Learning</topic><topic>Life Sciences</topic><topic>Neural networks</topic><topic>Original Paper</topic><topic>Pottery</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wilczek, Josef</creatorcontrib><creatorcontrib>Thér, Richard</creatorcontrib><creatorcontrib>Monna, Fabrice</creatorcontrib><creatorcontrib>Gentil, Christian</creatorcontrib><creatorcontrib>Roudet, Céline</creatorcontrib><creatorcontrib>Chateau-Smith, Carmela</creatorcontrib><collection>CrossRef</collection><collection>International Bibliography of the Social Sciences (IBSS)</collection><collection>ProQuest Central</collection><collection>ProQuest Central</collection><collection>Natural Science Collection</collection><collection>Earth, Atmospheric &amp; Aquatic Science Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>International Bibliography of the Social Sciences</collection><collection>SciTech Premium Collection</collection><collection>International Bibliography of the Social Sciences</collection><collection>Earth, Atmospheric &amp; Aquatic Science Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Hyper Article en Ligne (HAL)</collection><collection>HAL-SHS: Archive ouverte en Sciences de l'Homme et de la Société</collection><jtitle>Archaeological and anthropological sciences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wilczek, Josef</au><au>Thér, Richard</au><au>Monna, Fabrice</au><au>Gentil, Christian</au><au>Roudet, Céline</au><au>Chateau-Smith, Carmela</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Discrimination of wheel-thrown pottery surface treatment by Deep Learning</atitle><jtitle>Archaeological and anthropological sciences</jtitle><stitle>Archaeol Anthropol Sci</stitle><date>2022-05-01</date><risdate>2022</risdate><volume>14</volume><issue>5</issue><artnum>85</artnum><issn>1866-9557</issn><issn>1866-9565</issn><eissn>1866-9565</eissn><abstract>The study of pottery surface treatment is essential to understand techniques used by ancient potters, in order to explore the cultural and economic organisation of past societies. Pottery is one of the most abundant materials found in archaeological excavation, yet classification of pottery surface treatments remains challenging. The goal of this study is to propose a workflow to classify pottery surface treatments automatically, based on the extraction of images depicting surface geometry, calculated from 3D models. These images are then classified by Deep Learning. Three Convolutional Neural Network algorithms (VGG16 and VGG19 transfer learning, and a custom network) are quantitatively evaluated on an experimental dataset of 48 wheel-thrown vessels, created by a professional potter specifically for this study. To demonstrate workflow feasibility, six different surface treatments were applied to each vessel. Results obtained for all three classifiers (accuracy of 93 to 95%) surpass other state-of-the-art quantitative approaches proposed for pottery classification. The workflow is able to take into account the entire surface of the pottery, not only a pre-selected spatially limited area.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/s12520-022-01501-w</doi><orcidid>https://orcid.org/0000-0001-8633-5095</orcidid><orcidid>https://orcid.org/0000-0001-7771-2434</orcidid><orcidid>https://orcid.org/0000-0002-0704-081X</orcidid></addata></record>
fulltext fulltext
identifier ISSN: 1866-9557
ispartof Archaeological and anthropological sciences, 2022-05, Vol.14 (5), Article 85
issn 1866-9557
1866-9565
1866-9565
language eng
recordid cdi_hal_primary_oai_HAL_halshs_03823239v1
source International Bibliography of the Social Sciences (IBSS); Springer Nature
subjects Anthropology
Archaeology
Archaeology and Prehistory
Ceramics
Chemistry/Food Science
Classification
Deep learning
Discrimination
Earth and Environmental Science
Earth Sciences
Excavation
Extraction
Feasibility
Geography
Geometry
Humanities and Social Sciences
Learning
Life Sciences
Neural networks
Original Paper
Pottery
title Discrimination of wheel-thrown pottery surface treatment by Deep Learning
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T01%3A24%3A24IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_hal_p&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Discrimination%20of%20wheel-thrown%20pottery%20surface%20treatment%20by%20Deep%20Learning&rft.jtitle=Archaeological%20and%20anthropological%20sciences&rft.au=Wilczek,%20Josef&rft.date=2022-05-01&rft.volume=14&rft.issue=5&rft.artnum=85&rft.issn=1866-9557&rft.eissn=1866-9565&rft_id=info:doi/10.1007/s12520-022-01501-w&rft_dat=%3Cproquest_hal_p%3E2649214804%3C/proquest_hal_p%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c356t-f709fdfdb127fef5511b482cf51fa35c629e3ba814c37541ea7b6c0e9206cf743%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2649214804&rft_id=info:pmid/&rfr_iscdi=true