Large-scale interactive retrieval in art collections using multi-style feature aggregation

Finding objects and motifs across artworks is of great importance for art history as it helps to understand individual works and analyze relations between them. The advent of digitization has produced extensive digital art collections with many research opportunities. However, manual approaches are...

Full description

Saved in:
Bibliographic Details
Main Authors: Ufer, Nikolai (Author) , Simon, Max (Author) , Lang, Sabine (Author) , Ommer, Björn (Author)
Format: Article (Journal)
Language:English
Published: November 24, 2021
In: PLOS ONE
Year: 2021, Volume: 16, Issue: 11, Pages: 1-38
ISSN:1932-6203
DOI:10.1371/journal.pone.0259718
Online Access:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1371/journal.pone.0259718
Verlag, lizenzpflichtig, Volltext: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0259718
Get full text
Author Notes:Nikolai Ufer, Max Simon, Sabine Lang, Björn Ommer

MARC

LEADER 00000caa a2200000 c 4500
001 1793436223
003 DE-627
005 20220820133259.0
007 cr uuu---uuuuu
008 220221s2021 xx |||||o 00| ||eng c
024 7 |a 10.1371/journal.pone.0259718  |2 doi 
035 |a (DE-627)1793436223 
035 |a (DE-599)KXP1793436223 
035 |a (OCoLC)1341441781 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 28  |2 sdnb 
100 1 |a Ufer, Nikolai  |d 1984-  |e VerfasserIn  |0 (DE-588)1152282514  |0 (DE-627)101376398X  |0 (DE-576)499785347  |4 aut 
245 1 0 |a Large-scale interactive retrieval in art collections using multi-style feature aggregation  |c Nikolai Ufer, Max Simon, Sabine Lang, Björn Ommer 
264 1 |c November 24, 2021 
300 |a 38 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 21.02.2022 
520 |a Finding objects and motifs across artworks is of great importance for art history as it helps to understand individual works and analyze relations between them. The advent of digitization has produced extensive digital art collections with many research opportunities. However, manual approaches are inadequate to handle this amount of data, and it requires appropriate computer-based methods to analyze them. This article presents a visual search algorithm and user interface to support art historians to find objects and motifs in extensive datasets. Artistic image collections are subject to significant domain shifts induced by large variations in styles, artistic media, and materials. This poses new challenges to most computer vision models which are trained on photographs. To alleviate this problem, we introduce a multi-style feature aggregation that projects images into the same distribution, leading to more accurate and style-invariant search results. Our retrieval system is based on a voting procedure combined with fast nearest-neighbor search and enables finding and localizing motifs within an extensive image collection in seconds. The presented approach significantly improves the state-of-the-art in terms of accuracy and search time on various datasets and applies to large and inhomogeneous collections. In addition to the search algorithm, we introduce a user interface that allows art historians to apply our algorithm in practice. The interface enables users to search for single regions, multiple regions regarding different connection types and holds an interactive feedback system to improve retrieval results further. With our methodological contribution and easy-to-use user interface, this work manifests further progress towards a computer-based analysis of visual art. 
650 4 |a Algorithms 
650 4 |a Computer vision 
650 4 |a Historians 
650 4 |a Horses 
650 4 |a Information retrieval 
650 4 |a Lions 
650 4 |a Metadata 
650 4 |a User interfaces 
700 1 |a Simon, Max  |e VerfasserIn  |0 (DE-588)1237423945  |0 (DE-627)1764128222  |4 aut 
700 1 |a Lang, Sabine  |e VerfasserIn  |0 (DE-588)1100083812  |0 (DE-627)858973847  |0 (DE-576)469478187  |4 aut 
700 1 |a Ommer, Björn  |d 1981-  |e VerfasserIn  |0 (DE-588)1034893106  |0 (DE-627)746457510  |0 (DE-576)382507916  |4 aut 
773 0 8 |i Enthalten in  |t PLOS ONE  |d San Francisco, California, US : PLOS, 2006  |g 16(2021), 11, Artikel-ID e0259718, Seite 1-38  |h Online-Ressource  |w (DE-627)523574592  |w (DE-600)2267670-3  |w (DE-576)281331979  |x 1932-6203  |7 nnas  |a Large-scale interactive retrieval in art collections using multi-style feature aggregation 
773 1 8 |g volume:16  |g year:2021  |g number:11  |g elocationid:e0259718  |g pages:1-38  |g extent:38  |a Large-scale interactive retrieval in art collections using multi-style feature aggregation 
856 4 0 |u https://doi.org/10.1371/journal.pone.0259718  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
856 4 0 |u https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0259718  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20220221 
993 |a Article 
994 |a 2021 
998 |g 1034893106  |a Ommer, Björn  |m 1034893106:Ommer, Björn  |p 4  |y j 
998 |g 1100083812  |a Lang, Sabine  |m 1100083812:Lang, Sabine  |p 3 
998 |g 1237423945  |a Simon, Max  |m 1237423945:Simon, Max  |p 2 
998 |g 1152282514  |a Ufer, Nikolai  |m 1152282514:Ufer, Nikolai  |d 60000  |e 60000PU1152282514  |k 0/60000/  |p 1  |x j 
999 |a KXP-PPN1793436223  |e 4070847634 
BIB |a Y 
SER |a journal 
JSO |a {"physDesc":[{"extent":"38 S."}],"relHost":[{"disp":"Large-scale interactive retrieval in art collections using multi-style feature aggregationPLOS ONE","note":["Schreibweise des Titels bis 2012: PLoS ONE","Gesehen am 20.03.19"],"type":{"bibl":"periodical","media":"Online-Ressource"},"language":["eng"],"corporate":[{"roleDisplay":"Herausgebendes Organ","display":"Public Library of Science","role":"isb"}],"recId":"523574592","pubHistory":["1.2006 -"],"part":{"year":"2021","issue":"11","pages":"1-38","text":"16(2021), 11, Artikel-ID e0259718, Seite 1-38","volume":"16","extent":"38"},"title":[{"title_sort":"PLOS ONE","title":"PLOS ONE"}],"physDesc":[{"extent":"Online-Ressource"}],"name":{"displayForm":["Public Library of Science"]},"origin":[{"dateIssuedDisp":"2006-","dateIssuedKey":"2006","publisher":"PLOS ; PLoS","publisherPlace":"San Francisco, California, US ; Lawrence, Kan."}],"id":{"issn":["1932-6203"],"eki":["523574592"],"zdb":["2267670-3"]}}],"origin":[{"dateIssuedDisp":"November 24, 2021","dateIssuedKey":"2021"}],"id":{"doi":["10.1371/journal.pone.0259718"],"eki":["1793436223"]},"name":{"displayForm":["Nikolai Ufer, Max Simon, Sabine Lang, Björn Ommer"]},"type":{"bibl":"article-journal","media":"Online-Ressource"},"note":["Gesehen am 21.02.2022"],"recId":"1793436223","language":["eng"],"title":[{"title_sort":"Large-scale interactive retrieval in art collections using multi-style feature aggregation","title":"Large-scale interactive retrieval in art collections using multi-style feature aggregation"}],"person":[{"family":"Ufer","given":"Nikolai","display":"Ufer, Nikolai","roleDisplay":"VerfasserIn","role":"aut"},{"display":"Simon, Max","roleDisplay":"VerfasserIn","role":"aut","family":"Simon","given":"Max"},{"given":"Sabine","family":"Lang","role":"aut","display":"Lang, Sabine","roleDisplay":"VerfasserIn"},{"role":"aut","roleDisplay":"VerfasserIn","display":"Ommer, Björn","given":"Björn","family":"Ommer"}]} 
SRT |a UFERNIKOLALARGESCALE2420