Unsupervised learning with a physics-based autoencoder for estimating the thickness and mixing ratio of pigments

Layered surface objects represented by decorated tomb murals and watercolors are in danger of deterioration and damage. To address these dangers, it is necessary to analyze the pigments' thickness and mixing ratio and record the current status. This paper proposes an unsupervised autoencoder mo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of the Optical Society of America. A, Optics, image science, and vision Jg. 40; H. 1; S. 116
Hauptverfasser: Shitomi, Ryuta, Tsuji, Mayuka, Fujimura, Yuki, Funatomi, Takuya, Mukaigawa, Yasuhiro, Morimoto, Tetsuro, Oishi, Takeshi, Takamatsu, Jun, Ikeuchi, Katsushi
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States 01.01.2023
ISSN:1520-8532, 1520-8532
Online-Zugang:Weitere Angaben
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Layered surface objects represented by decorated tomb murals and watercolors are in danger of deterioration and damage. To address these dangers, it is necessary to analyze the pigments' thickness and mixing ratio and record the current status. This paper proposes an unsupervised autoencoder model for thickness and mixing ratio estimation. The input of our autoencoder is spectral data of layered surface objects. Our autoencoder is unique, to our knowledge, in that the decoder part uses a physical model, the Kubelka-Munk model. Since we use the Kubelka-Munk model for the decoder, latent variables in the middle layer can be interpretable as the pigment thickness and mixing ratio. We conducted a quantitative evaluation using synthetic data and confirmed that our autoencoder provides a highly accurate estimation. We measured an object with layered surface pigments for qualitative evaluation and confirmed that our method is valid in an actual environment. We also present the superiority of our unsupervised autoencoder over supervised learning.
AbstractList Layered surface objects represented by decorated tomb murals and watercolors are in danger of deterioration and damage. To address these dangers, it is necessary to analyze the pigments' thickness and mixing ratio and record the current status. This paper proposes an unsupervised autoencoder model for thickness and mixing ratio estimation. The input of our autoencoder is spectral data of layered surface objects. Our autoencoder is unique, to our knowledge, in that the decoder part uses a physical model, the Kubelka-Munk model. Since we use the Kubelka-Munk model for the decoder, latent variables in the middle layer can be interpretable as the pigment thickness and mixing ratio. We conducted a quantitative evaluation using synthetic data and confirmed that our autoencoder provides a highly accurate estimation. We measured an object with layered surface pigments for qualitative evaluation and confirmed that our method is valid in an actual environment. We also present the superiority of our unsupervised autoencoder over supervised learning.
Layered surface objects represented by decorated tomb murals and watercolors are in danger of deterioration and damage. To address these dangers, it is necessary to analyze the pigments' thickness and mixing ratio and record the current status. This paper proposes an unsupervised autoencoder model for thickness and mixing ratio estimation. The input of our autoencoder is spectral data of layered surface objects. Our autoencoder is unique, to our knowledge, in that the decoder part uses a physical model, the Kubelka-Munk model. Since we use the Kubelka-Munk model for the decoder, latent variables in the middle layer can be interpretable as the pigment thickness and mixing ratio. We conducted a quantitative evaluation using synthetic data and confirmed that our autoencoder provides a highly accurate estimation. We measured an object with layered surface pigments for qualitative evaluation and confirmed that our method is valid in an actual environment. We also present the superiority of our unsupervised autoencoder over supervised learning.Layered surface objects represented by decorated tomb murals and watercolors are in danger of deterioration and damage. To address these dangers, it is necessary to analyze the pigments' thickness and mixing ratio and record the current status. This paper proposes an unsupervised autoencoder model for thickness and mixing ratio estimation. The input of our autoencoder is spectral data of layered surface objects. Our autoencoder is unique, to our knowledge, in that the decoder part uses a physical model, the Kubelka-Munk model. Since we use the Kubelka-Munk model for the decoder, latent variables in the middle layer can be interpretable as the pigment thickness and mixing ratio. We conducted a quantitative evaluation using synthetic data and confirmed that our autoencoder provides a highly accurate estimation. We measured an object with layered surface pigments for qualitative evaluation and confirmed that our method is valid in an actual environment. We also present the superiority of our unsupervised autoencoder over supervised learning.
Author Fujimura, Yuki
Ikeuchi, Katsushi
Tsuji, Mayuka
Mukaigawa, Yasuhiro
Funatomi, Takuya
Morimoto, Tetsuro
Shitomi, Ryuta
Oishi, Takeshi
Takamatsu, Jun
Author_xml – sequence: 1
  givenname: Ryuta
  surname: Shitomi
  fullname: Shitomi, Ryuta
– sequence: 2
  givenname: Mayuka
  surname: Tsuji
  fullname: Tsuji, Mayuka
– sequence: 3
  givenname: Yuki
  surname: Fujimura
  fullname: Fujimura, Yuki
– sequence: 4
  givenname: Takuya
  surname: Funatomi
  fullname: Funatomi, Takuya
– sequence: 5
  givenname: Yasuhiro
  surname: Mukaigawa
  fullname: Mukaigawa, Yasuhiro
– sequence: 6
  givenname: Tetsuro
  surname: Morimoto
  fullname: Morimoto, Tetsuro
– sequence: 7
  givenname: Takeshi
  surname: Oishi
  fullname: Oishi, Takeshi
– sequence: 8
  givenname: Jun
  surname: Takamatsu
  fullname: Takamatsu, Jun
– sequence: 9
  givenname: Katsushi
  surname: Ikeuchi
  fullname: Ikeuchi, Katsushi
BackLink https://www.ncbi.nlm.nih.gov/pubmed/36607080$$D View this record in MEDLINE/PubMed
BookMark eNpNkLtPwzAQhy1URB-wMSOPLAHH8SMeq4qnKnWAzpHrXFpDYgc7Afrfk4oiMZzupO_T6Xc3RSPnHSB0mZKbNBPs9nn1Mp_fMEml5CdoknJKkpxndPRvHqNpjG-EECZyeYbGmRBEkpxMULt2sW8hfNoIJa5BB2fdFn_Zboc1bnf7aE1MNvpAdd95cMaXEHDlA4bY2UZ3B7_bwVDWvDuIEWtX4sZ-H0AYuMe-wq3dNuC6eI5OK11HuDj2GVrf370uHpPl6uFpMV8mhqq0SzSnUCkAMcRnpTKasYxVoMBUginKN4rrKssHmQijUzCguWQ6FwJkpiCnM3T9u7cN_qMfohaNjQbqWjvwfSyoFKnKueR8UK-Oar9poCzaMJwV9sXfl-gPdNxtRw
CitedBy_id crossref_primary_10_1038_s40494_025_01924_3
crossref_primary_10_3390_app14093938
crossref_primary_10_3390_s23052419
ContentType Journal Article
DBID NPM
7X8
DOI 10.1364/JOSAA.472775
DatabaseName PubMed
MEDLINE - Academic
DatabaseTitle PubMed
MEDLINE - Academic
DatabaseTitleList PubMed
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod no_fulltext_linktorsrc
Discipline Physics
EISSN 1520-8532
ExternalDocumentID 36607080
Genre Journal Article
GroupedDBID ---
-DZ
-~X
29L
4.4
5GY
AAWJZ
AEDJG
AKGWG
ALMA_UNASSIGNED_HOLDINGS
ATHME
AYPRP
AZSQR
AZYMN
CS3
DSZJF
EBS
F5P
NPM
ODPQJ
OFLFD
OPJBK
OPLUZ
PZZ
RNS
ROL
ROP
ROS
S10
TR6
UCJ
WH7
XSW
7X8
ID FETCH-LOGICAL-c291t-a52ef9ee68534d9ca4434fe9ecf64925b95af38c2906ca1ecea574a866e739e82
IEDL.DBID 7X8
ISICitedReferencesCount 5
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000906447400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1520-8532
IngestDate Fri Jul 11 16:12:13 EDT 2025
Wed Feb 19 02:25:12 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c291t-a52ef9ee68534d9ca4434fe9ecf64925b95af38c2906ca1ecea574a866e739e82
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
PMID 36607080
PQID 2761985755
PQPubID 23479
ParticipantIDs proquest_miscellaneous_2761985755
pubmed_primary_36607080
PublicationCentury 2000
PublicationDate 2023-Jan-01
20230101
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – month: 01
  year: 2023
  text: 2023-Jan-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle Journal of the Optical Society of America. A, Optics, image science, and vision
PublicationTitleAlternate J Opt Soc Am A Opt Image Sci Vis
PublicationYear 2023
SSID ssj0004687
Score 2.4215548
Snippet Layered surface objects represented by decorated tomb murals and watercolors are in danger of deterioration and damage. To address these dangers, it is...
SourceID proquest
pubmed
SourceType Aggregation Database
Index Database
StartPage 116
Title Unsupervised learning with a physics-based autoencoder for estimating the thickness and mixing ratio of pigments
URI https://www.ncbi.nlm.nih.gov/pubmed/36607080
https://www.proquest.com/docview/2761985755
Volume 40
WOSCitedRecordID wos000906447400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1La9tAEF7SuoVc-kwT9xE20OvWsvah3VMxpaYU4hgag29iH7PGlEpqZIf8_OxIMu0lUOhFF0kgRqP5vp0dfR8hH6102moLrEjoykQhNHO5BKZcnErHuQsgOrOJYrHQ67VZDg23dhirPNTErlCH2mOPfJLjehvtJOXn5jdD1yjcXR0sNB6REU9UBke6ivVfauGqM8hLEJWxBEv5MPjOlZh8v_oxm30SCb0L-TC57EBm_vx_H-8FeTbQSzrr8-ElOYLqFXnajXn69jVpVlW7b7A8tBDo4BixodiMpZb2XY6WIbIFave7GlUuA9zQxGwpynEgvU3XJ9JIcU7-J9ZJaqtAf23v8ESXTrSOtNluun_nTshq_vX6yzc2eC4wn5vpjlmZQzQAKsVLBOOtEFxEMOCjQh1DZ6SNXHtUifd2Ch6sLITVSkHBDej8DXlc1RWcEaqy4I0JeSF9WrVpZ2LGnc1Q4F4LE_mYXBxCWaacxo0KW0G9b8s_wRyT0_59lE0vvlFypVKV0tnbf7j7HTlGd_i-Y_KejGL6ouEDeeJvd9v25rxLlnRcLC_vAfdGy_8
linkProvider ProQuest
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=Unsupervised+learning+with+a+physics-based+autoencoder+for+estimating+the+thickness+and+mixing+ratio+of+pigments&rft.jtitle=Journal+of+the+Optical+Society+of+America.+A%2C+Optics%2C+image+science%2C+and+vision&rft.au=Shitomi%2C+Ryuta&rft.au=Tsuji%2C+Mayuka&rft.au=Fujimura%2C+Yuki&rft.au=Funatomi%2C+Takuya&rft.date=2023-01-01&rft.eissn=1520-8532&rft.volume=40&rft.issue=1&rft.spage=116&rft_id=info:doi/10.1364%2FJOSAA.472775&rft_id=info%3Apmid%2F36607080&rft_id=info%3Apmid%2F36607080&rft.externalDocID=36607080
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1520-8532&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1520-8532&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1520-8532&client=summon