Automated detection and classification of multi-cell Phytoliths using Deep Learning-Based Algorithms

This paper presents an algorithm for automated detection and classification of multi-cell phytoliths, one of the major components of many archaeological and paleoenvironmental deposits. This identification, based on phytolith wave pattern, is made using a pretrained VGG19 deep learning model. This a...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Journal of archaeological science Ročník 148; s. 105654
Hlavní autori:	Berganzo-Besga, Iban, Orengo, Hector A., Lumbreras, Felipe, Aliende, Paloma, Ramsey, Monica N.
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier Ltd 01.12.2022
Predmet:	algorithms archaeology automation color Computational archaeology Deep learning Google colaboratory Hordeum Machine learning Middle East paleoecology Phytoliths species Triticum monococcum subsp. aegilopoides Middle East Deep learning Phytoliths Google colaboratory Computational archaeology Machine learning
ISSN:	0305-4403
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	This paper presents an algorithm for automated detection and classification of multi-cell phytoliths, one of the major components of many archaeological and paleoenvironmental deposits. This identification, based on phytolith wave pattern, is made using a pretrained VGG19 deep learning model. This approach has been tested in three key phytolith genera for the study of agricultural origins in Near East archaeology: Avena, Hordeum and Triticum. Also, this classification has been validated at species-level using Triticum boeoticum and dicoccoides images. Due to the diversity of microscopes, cameras and chemical treatments that can influence images of phytolith slides, three types of data augmentation techniques have been implemented: rotation of the images at 45-degree angles, random colour and brightness jittering, and random blur/sharpen. The implemented workflow has resulted in an overall accuracy of 93.68% for phytolith genera, improving previous attempts. The algorithm has also demonstrated its potential to automatize the classification of phytoliths species with an overall accuracy of 100%. The open code and platforms employed to develop the algorithm assure the method's accessibility, reproducibility and reusability. •Deep learning automates identification and classification of multi-cell phytoliths.•Can be applied to digitalised slides and integrated into digital microscopes.•Can differentiate between phytolith genera but also species.•Presents an overall accuracy of 93% and analyses the whole slide.•Provides complementary metrics with new relevant information on phytoliths.
AbstractList	This paper presents an algorithm for automated detection and classification of multi-cell phytoliths, one of the major components of many archaeological and paleoenvironmental deposits. This identification, based on phytolith wave pattern, is made using a pretrained VGG19 deep learning model. This approach has been tested in three key phytolith genera for the study of agricultural origins in Near East archaeology: Avena, Hordeum and Triticum. Also, this classification has been validated at species-level using Triticum boeoticum and dicoccoides images. Due to the diversity of microscopes, cameras and chemical treatments that can influence images of phytolith slides, three types of data augmentation techniques have been implemented: rotation of the images at 45-degree angles, random colour and brightness jittering, and random blur/sharpen. The implemented workflow has resulted in an overall accuracy of 93.68% for phytolith genera, improving previous attempts. The algorithm has also demonstrated its potential to automatize the classification of phytoliths species with an overall accuracy of 100%. The open code and platforms employed to develop the algorithm assure the method's accessibility, reproducibility and reusability. This paper presents an algorithm for automated detection and classification of multi-cell phytoliths, one of the major components of many archaeological and paleoenvironmental deposits. This identification, based on phytolith wave pattern, is made using a pretrained VGG19 deep learning model. This approach has been tested in three key phytolith genera for the study of agricultural origins in Near East archaeology: Avena, Hordeum and Triticum. Also, this classification has been validated at species-level using Triticum boeoticum and dicoccoides images. Due to the diversity of microscopes, cameras and chemical treatments that can influence images of phytolith slides, three types of data augmentation techniques have been implemented: rotation of the images at 45-degree angles, random colour and brightness jittering, and random blur/sharpen. The implemented workflow has resulted in an overall accuracy of 93.68% for phytolith genera, improving previous attempts. The algorithm has also demonstrated its potential to automatize the classification of phytoliths species with an overall accuracy of 100%. The open code and platforms employed to develop the algorithm assure the method's accessibility, reproducibility and reusability. •Deep learning automates identification and classification of multi-cell phytoliths.•Can be applied to digitalised slides and integrated into digital microscopes.•Can differentiate between phytolith genera but also species.•Presents an overall accuracy of 93% and analyses the whole slide.•Provides complementary metrics with new relevant information on phytoliths.
ArticleNumber	105654
Author	Ramsey, Monica N. Lumbreras, Felipe Aliende, Paloma Berganzo-Besga, Iban Orengo, Hector A.
Author_xml	– sequence: 1 givenname: Iban surname: Berganzo-Besga fullname: Berganzo-Besga, Iban organization: Landscape Archaeology Research Group, Catalan Institute of Classical Archaeology, Pl. Rovellat s/n, 43003, Tarragona, Spain – sequence: 2 givenname: Hector A. orcidid: 0000-0002-9385-2370 surname: Orengo fullname: Orengo, Hector A. email: horengo@icac.cat organization: Landscape Archaeology Research Group, Catalan Institute of Classical Archaeology, Pl. Rovellat s/n, 43003, Tarragona, Spain – sequence: 3 givenname: Felipe surname: Lumbreras fullname: Lumbreras, Felipe organization: Computer Vision Center, Computer Science Department, Universitat Autònoma de Barcelona, Edifici O, Campus UAB, 08193, Bellaterra, Spain – sequence: 4 givenname: Paloma surname: Aliende fullname: Aliende, Paloma organization: Landscape Archaeology Research Group, Catalan Institute of Classical Archaeology, Pl. Rovellat s/n, 43003, Tarragona, Spain – sequence: 5 givenname: Monica N. surname: Ramsey fullname: Ramsey, Monica N. organization: McDonald Institute for Archaeological Research, University of Cambridge, Downing Street, Cambridge, CB2 3ER, UK
BookMark	eNp9kD1PwzAQhj0UibbwA9g8sqTYcT4aMZXyKVWCAWbLsS-tIycutoPUf4_bMDFUN5zOep_T-ZmhSW97QOiGkgUltLhrF63wi5SkaZzzIs8maEoYyZMsI-wSzbxvCaE0z9MpUqsh2E4EUFhBABm07bHoFZZGeK8bLcXpyTa4G0zQiQRj8MfuEKzRYefx4HW_xY8Ae7wB4fo4JQ_Cx30rs7UuZjp_hS4aYTxc__U5-np--ly_Jpv3l7f1apNIxkhIqAQmakVI01RVJaoMMgBI65rVBUtpI2M1BQWpAEi2FLRidQolK6AoaUEyNke34969s98D-MA77Y8Hix7s4Hla0iXLlyUlMUrHqHTWewcN3zvdCXfglPCjRd7yaJEfLfLRYmTKf4zU4aQnOKHNWfJ-JCH-_keD415q6CUo7aJzrqw-Q_8CH1CSkg
CitedBy_id	crossref_primary_10_4108_eetpht_10_5477 crossref_primary_10_1093_aob_mcae116 crossref_primary_10_1007_s00334_023_00908_2 crossref_primary_10_1016_j_microc_2024_112243 crossref_primary_10_1007_s12145_023_00975_z crossref_primary_10_1007_s13748_024_00331_2 crossref_primary_10_1038_s41598_023_38190_x crossref_primary_10_1016_j_jas_2025_106244 crossref_primary_10_1093_aob_mcaf088
Cites_doi	10.1017/S1431927620024629 10.1007/s12520-016-0341-0 10.1371/journal.pone.0004448 10.1093/aob/mcaa102 10.1016/j.quaint.2007.11.008 10.3389/fpls.2019.01736 10.1093/aob/mcz064 10.1007/s12520-014-0190-7 10.3390/rs13204181 10.1111/jse.12258
ContentType	Journal Article
Copyright	2022
Copyright_xml	– notice: 2022
DBID	AAYXX CITATION 7S9 L.6
DOI	10.1016/j.jas.2022.105654
DatabaseName	CrossRef AGRICOLA AGRICOLA - Academic
DatabaseTitle	CrossRef AGRICOLA AGRICOLA - Academic
DatabaseTitleList	AGRICOLA
DeliveryMethod	fulltext_linktorsrc
Discipline	History & Archaeology
ExternalDocumentID	10_1016_j_jas_2022_105654 S0305440322001121
GeographicLocations	Middle East
GeographicLocations_xml	– name: Middle East
GroupedDBID	--K --M .~1 0R~ 1B1 1RT 1~. 1~5 29J 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JO AABNK AABXZ AACJB AACTN AAEDT AAEDW AAFJI AAHBH AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO ABFNM ABJNI ABMAC ABMMH ABWVN ABXDB ABXRA ACDAQ ACGFS ACHQT ACNNM ACRLP ACRPL ADBBV ADEZE ADFGL ADMHG ADMUD ADNMO AEBSH AEIPS AEKER AENEX AETEA AEZYN AFJKZ AFRZQ AFTJW AFXIZ AGHFR AGQPQ AGUBO AGYEJ AHHHB AIEXJ AIKHN AITUG AKRWK ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOMHK APXCP ASPBG AVARZ AVWKF AXJTR AZFZN BKOJK BLXMC BNPGV CAG COF CS3 DM4 DU5 EBS EFBJH EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA HMY HVGLF HZ~ H~9 IHE J1W KOM LG5 LPU M3X M41 MAGPM MO0 MVM N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PRBVW Q38 R2- RIG ROL RPZ SCC SDF SDG SDP SES SEW SPC SPCBC SSB SSH SSM SSO SSS SSZ T5K TN5 VJK WUQ XOL XPP YQT ZCG ZMT ZU3 ~02 ~G- 9DU AAYWO AAYXX ABUFD ACLOT ACVFH ADCNI ADXHL AEUPX AFPUW AIGII AIIUN AKBMS AKYEP CITATION EFKBS EFLBG ~HD 7S9 L.6
ID	FETCH-LOGICAL-c330t-1ce3abd00ff999a94e4eee2bb3b6321fcfcff61ecdee048a193b2e736e6716043
ISICitedReferencesCount	11
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000891291000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0305-4403
IngestDate	Thu Oct 02 22:54:21 EDT 2025 Tue Nov 18 22:18:51 EST 2025 Sat Nov 29 08:02:21 EST 2025 Sat Apr 19 15:52:52 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Keywords	Deep learning Phytoliths Google colaboratory Computational archaeology Machine learning
Language	English
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c330t-1ce3abd00ff999a94e4eee2bb3b6321fcfcff61ecdee048a193b2e736e6716043
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0002-9385-2370
PQID	2718358710
PQPubID	24069
ParticipantIDs	proquest_miscellaneous_2718358710 crossref_primary_10_1016_j_jas_2022_105654 crossref_citationtrail_10_1016_j_jas_2022_105654 elsevier_sciencedirect_doi_10_1016_j_jas_2022_105654
PublicationCentury	2000
PublicationDate	December 2022 2022-12-00 20221201
PublicationDateYYYYMMDD	2022-12-01
PublicationDate_xml	– month: 12 year: 2022 text: December 2022
PublicationDecade	2020
PublicationTitle	Journal of archaeological science
PublicationYear	2022
Publisher	Elsevier Ltd
Publisher_xml	– name: Elsevier Ltd
References	Orengo, Garcia-Molsosa, Berganzo-Besga, Landauer, Aliende, Tres-Martínez (bib11) 2021 Hošková, Pokorná, Neustupa, Pokorný (bib8) 2021; 127 Rapp, Mulholland (bib14) 1992 Battiato, Guarnera, Ortis, Trenta, Ascari, Siniscalco, De Gregorio, Suárez (bib2) 2021 Lu, Zhang, Wu, Liu, Xu, Li (bib10) 2009; 4 Rosen (bib15) 1992; ume 1 (bib9) 2019; 124 Anichini, Banterle, Buxeda i Garrigós, Callieri, Dershowitz, Dubbini, Lucendo, Evans, Gattiglia, Green, Gualandi, Hervas, Itkin, Madrid i Fernandez, Miguel, Remmy, Richards, Scopigno, Vila, Wolf, Wright, Zallocco (bib1) 2020; 52 Cai, Ge (bib4) 2017; 55 Strömberg (bib16) 2009; 193 Ge, Lu, Zhang, Wang, He, Huan (bib6) 2018; 10 (bib12) 2019 Waleed (bib18) 2017 Weisskopf, Lee (bib19) 2016; 8 Torres (bib17) 2020 Piperno (bib13) 2006 Berganzo-Besga, Orengo, Lumbreras, Carrero-Pazos, Fonte, Vilas-Estévez (bib3) 2021; 13 Ge (bib7) 2019; 10 Díez-Pastor, Latorre-Carmona, Arnaiz-González, Ruiz-Pérez, Zurro (bib5) 2020; 26 Ge (10.1016/j.jas.2022.105654_bib7) 2019; 10 Lu (10.1016/j.jas.2022.105654_bib10) 2009; 4 Díez-Pastor (10.1016/j.jas.2022.105654_bib5) 2020; 26 Rosen (10.1016/j.jas.2022.105654_bib15) 1992; ume 1 Orengo (10.1016/j.jas.2022.105654_bib11) 2021 Berganzo-Besga (10.1016/j.jas.2022.105654_bib3) 2021; 13 Strömberg (10.1016/j.jas.2022.105654_bib16) 2009; 193 Battiato (10.1016/j.jas.2022.105654_bib2) 2021 Anichini (10.1016/j.jas.2022.105654_bib1) 2020; 52 (10.1016/j.jas.2022.105654_bib12) 2019 Ge (10.1016/j.jas.2022.105654_bib6) 2018; 10 Hošková (10.1016/j.jas.2022.105654_bib8) 2021; 127 Waleed (10.1016/j.jas.2022.105654_bib18) 2017 Torres (10.1016/j.jas.2022.105654_bib17) 2020 Cai (10.1016/j.jas.2022.105654_bib4) 2017; 55 Piperno (10.1016/j.jas.2022.105654_bib13) 2006 (10.1016/j.jas.2022.105654_bib9) 2019; 124 Weisskopf (10.1016/j.jas.2022.105654_bib19) 2016; 8 Rapp (10.1016/j.jas.2022.105654_bib14) 1992
References_xml	– volume: 193 start-page: 124 year: 2009 end-page: 140 ident: bib16 article-title: Methodological concerns for analysis of phytolith assemblages: does count size matter? publication-title: Quat. Int. – start-page: 231 year: 2020 end-page: 253 ident: bib17 article-title: Python Deep Learning. Introducción Práctica con Keras y TensorFlow2 – volume: 10 start-page: 1736 year: 2019 ident: bib7 article-title: Phytoliths in inflorescence bracts: preliminary results of an investigation on common panicoideae plants in China publication-title: Front. Plant Sci. – volume: 13 start-page: 4181 year: 2021 ident: bib3 article-title: Hybrid MSRM-based deep learning and multitemporal sentinel 2-based machine learning algorithm detects near 10k archaeological tumuli in North-Western Iberia publication-title: Rem. Sens. – start-page: 1 year: 2021 end-page: 8 ident: bib11 article-title: New developments in drone-based automated surface survey: towards a functional and effective survey system publication-title: Archaeol. Prospect. – year: 2006 ident: bib13 article-title: Phytoliths: A Comprehensive Guide for Archaeologists and Paleoecologists – volume: 55 start-page: 377 year: 2017 end-page: 384 ident: bib4 article-title: Machine learning algorithms improve the power of phytolith analysis: a case study of the tribe Oryzeae (Poaceae) publication-title: J. Systemat. Evol. – volume: 26 start-page: 1158 year: 2020 end-page: 1167 ident: bib5 article-title: You Are Not My Type”: An Evaluation of Classification Methods for Automatic Phytolith Identification publication-title: Microsc. Microanal. – start-page: 469 year: 2021 end-page: 479 ident: bib2 article-title: Pollen grain classification challenge 2020 publication-title: Pattern Recognition. ICPR International Workshops and Challenges – volume: 127 start-page: 191 year: 2021 end-page: 201 ident: bib8 article-title: Inter- and intraspecific variation in grass phytolith shape and size: a geometric morphometrics perspective publication-title: Ann. Bot. – volume: 124 start-page: 189 year: 2019 end-page: 199 ident: bib9 article-title: International code for phytolith nomenclature (ICPN) 2.0 publication-title: Ann. Bot. – volume: 10 start-page: 61 year: 2018 end-page: 73 ident: bib6 article-title: Phytolith analysis for the identification of barnyard millet ( publication-title: Archaeol. Anthropol. Sci. – volume: 52 year: 2020 ident: bib1 article-title: Developing the ArchAIDE Application: a digital workflow for identifying, organising and sharing archaeological pottery using automated image recognition publication-title: Internet Archaeol. – volume: 4 start-page: e4448 year: 2009 ident: bib10 article-title: Phytoliths analysis for the discrimination of foxtail millet ( publication-title: PLoS One – volume: ume 1 start-page: 129 year: 1992 end-page: 147 ident: bib15 article-title: Preliminary identification of silica skeletons from near eastern archaeological sites: an anatomical approach publication-title: Phytolith Systematics: Emerging Issues. Advances in Archaeological and Museum Science – year: 1992 ident: bib14 article-title: Phytolith Systematics: Emerging Issues. Advances in Archaeological and Museum Science – year: 2017 ident: bib18 article-title: Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow – year: 2019 ident: bib12 article-title: Phytolith Automatic Identification System” v.0.2 – volume: 8 start-page: 29 year: 2016 end-page: 42 ident: bib19 article-title: Phytolith identification criteria for foxtail and broomcorn millets: a new approach to calculating crop ratios publication-title: Archaeol. Anthropol. Sci. – volume: 26 start-page: 1158 issue: 6 year: 2020 ident: 10.1016/j.jas.2022.105654_bib5 article-title: You Are Not My Type”: An Evaluation of Classification Methods for Automatic Phytolith Identification publication-title: Microsc. Microanal. doi: 10.1017/S1431927620024629 – volume: 10 start-page: 61 year: 2018 ident: 10.1016/j.jas.2022.105654_bib6 article-title: Phytolith analysis for the identification of barnyard millet (Echinochloa sp.) and its implications publication-title: Archaeol. Anthropol. Sci. doi: 10.1007/s12520-016-0341-0 – volume: 4 start-page: e4448 issue: 2 year: 2009 ident: 10.1016/j.jas.2022.105654_bib10 article-title: Phytoliths analysis for the discrimination of foxtail millet (Setaria italica) and common millet (Panicum miliaceum) publication-title: PLoS One doi: 10.1371/journal.pone.0004448 – start-page: 1 year: 2021 ident: 10.1016/j.jas.2022.105654_bib11 article-title: New developments in drone-based automated surface survey: towards a functional and effective survey system publication-title: Archaeol. Prospect. – year: 2019 ident: 10.1016/j.jas.2022.105654_bib12 – volume: 127 start-page: 191 issue: 2 year: 2021 ident: 10.1016/j.jas.2022.105654_bib8 article-title: Inter- and intraspecific variation in grass phytolith shape and size: a geometric morphometrics perspective publication-title: Ann. Bot. doi: 10.1093/aob/mcaa102 – volume: 193 start-page: 124 issue: 1–2 year: 2009 ident: 10.1016/j.jas.2022.105654_bib16 article-title: Methodological concerns for analysis of phytolith assemblages: does count size matter? publication-title: Quat. Int. doi: 10.1016/j.quaint.2007.11.008 – volume: 10 start-page: 1736 year: 2019 ident: 10.1016/j.jas.2022.105654_bib7 article-title: Phytoliths in inflorescence bracts: preliminary results of an investigation on common panicoideae plants in China publication-title: Front. Plant Sci. doi: 10.3389/fpls.2019.01736 – volume: 124 start-page: 189 issue: 2 year: 2019 ident: 10.1016/j.jas.2022.105654_bib9 article-title: International code for phytolith nomenclature (ICPN) 2.0 publication-title: Ann. Bot. doi: 10.1093/aob/mcz064 – volume: 8 start-page: 29 issue: 1 year: 2016 ident: 10.1016/j.jas.2022.105654_bib19 article-title: Phytolith identification criteria for foxtail and broomcorn millets: a new approach to calculating crop ratios publication-title: Archaeol. Anthropol. Sci. doi: 10.1007/s12520-014-0190-7 – year: 1992 ident: 10.1016/j.jas.2022.105654_bib14 – volume: ume 1 start-page: 129 year: 1992 ident: 10.1016/j.jas.2022.105654_bib15 article-title: Preliminary identification of silica skeletons from near eastern archaeological sites: an anatomical approach – start-page: 231 year: 2020 ident: 10.1016/j.jas.2022.105654_bib17 – volume: 52 year: 2020 ident: 10.1016/j.jas.2022.105654_bib1 article-title: Developing the ArchAIDE Application: a digital workflow for identifying, organising and sharing archaeological pottery using automated image recognition publication-title: Internet Archaeol. – year: 2006 ident: 10.1016/j.jas.2022.105654_bib13 – volume: 13 start-page: 4181 year: 2021 ident: 10.1016/j.jas.2022.105654_bib3 article-title: Hybrid MSRM-based deep learning and multitemporal sentinel 2-based machine learning algorithm detects near 10k archaeological tumuli in North-Western Iberia publication-title: Rem. Sens. doi: 10.3390/rs13204181 – start-page: 469 year: 2021 ident: 10.1016/j.jas.2022.105654_bib2 article-title: Pollen grain classification challenge 2020 – volume: 55 start-page: 377 issue: 4 year: 2017 ident: 10.1016/j.jas.2022.105654_bib4 article-title: Machine learning algorithms improve the power of phytolith analysis: a case study of the tribe Oryzeae (Poaceae) publication-title: J. Systemat. Evol. doi: 10.1111/jse.12258 – year: 2017 ident: 10.1016/j.jas.2022.105654_bib18
SSID	ssj0011552
Score	2.4277923
Snippet	This paper presents an algorithm for automated detection and classification of multi-cell phytoliths, one of the major components of many archaeological and...
SourceID	proquest crossref elsevier
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	105654
SubjectTerms	algorithms archaeology automation color Computational archaeology Deep learning Google colaboratory Hordeum Machine learning Middle East paleoecology Phytoliths species Triticum monococcum subsp. aegilopoides
Title	Automated detection and classification of multi-cell Phytoliths using Deep Learning-Based Algorithms
URI	https://dx.doi.org/10.1016/j.jas.2022.105654 https://www.proquest.com/docview/2718358710
Volume	148
WOSCitedRecordID	wos000891291000001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVESC databaseName: ScienceDirect Freedom Collection - Elsevier issn: 0305-4403 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0011552 providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6FlAMXxKOI8tIioR6ItnLW76MLiSiq0h5SKTfLux63jVLbJE7VcOGvM-td26RAVQ4okhVZ4yTa-bLzzc6LkA9hKl0RJhYDIXzmIGFliZcGDIahK4a4KQduVg-b8CeTYDYLT3u9H00tzPXCz_Pg5iYs_6uq8R4qW5XO_oO62w_FG_gelY5XVDte76X4aF0VSEORSKZQgZkErorXFE9WiUEtSayTCZmsT-8uNpXKhLtYDdb16cFngLJpvnrODtHWpYNocV4sUcY0OP-d0taNl6DdTo11bT1-UHWf3wt2CCt9nHskOmyeLCE_L7QlVIGEQXTQJgutr9BxX-rSszEsLssOp0ihc905-DRZFMbImFMMzn_JCDHVW5bLHMeyt3ZmJxiUahKx5zrsj_u9PnqYH8wT1XqdcyPcGbcmoD85icdnx8fxdDSb7pffmBo7psLzZgbLA7LDfTcM-mQnOhrNvraBKNWhTgei9M9rAuN1iuCtb_0btbll5GvmMn1CHhv90EhD5SnpQf6M7Or-MBu6T6NWa5vnJG3hQ1v4UIQP3YYPLTLawYd28KE1fKiCD92GD-3gs0vOxqPppy_MTOJg0ratig0l2IlILSvL0KFIQgccAOBC2MKz-TCT-Mq8IcgUAE1Cgl6B4ODbHnjoj1uO_YL08yKHl4R6rhtIIZ1Mct9JLE_wEKVsHiZ25gk_3CNWs4ixNG3q1bSURdzkI85jXPdYrXus132PfGwfKXWPlruEnUYzsfkbaPIYI6bueux9o8UYN2C1tkkOxRqFkN3ZboBM_dU9ZF6TRx3835B-tVzDW_JQXleXq-U7g76f0_isJg
linkProvider	Elsevier
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Automated+detection+and+classification+of+multi-cell+Phytoliths+using+Deep+Learning-Based+Algorithms&rft.jtitle=Journal+of+archaeological+science&rft.au=Berganzo-Besga%2C+Iban&rft.au=Orengo%2C+Hector+A.&rft.au=Lumbreras%2C+Felipe&rft.au=Aliende%2C+Paloma&rft.date=2022-12-01&rft.issn=0305-4403&rft.volume=148+p.105654-&rft_id=info:doi/10.1016%2Fj.jas.2022.105654&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0305-4403&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0305-4403&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0305-4403&client=summon