Cargando…

Compare the performance of the models in art classification

Because large numbers of artworks are preserved in museums and galleries, much work must be done to classify these works into genres, styles and artists. Recent technological advancements have enabled an increasing number of artworks to be digitized. Thus, it is necessary to teach computers to analy...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhao, Wentao, Zhou, Dalin, Qiu, Xinguo, Jiang, Wei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7954342/
https://www.ncbi.nlm.nih.gov/pubmed/33711046
http://dx.doi.org/10.1371/journal.pone.0248414
_version_ 1783664060599894016
author Zhao, Wentao
Zhou, Dalin
Qiu, Xinguo
Jiang, Wei
author_facet Zhao, Wentao
Zhou, Dalin
Qiu, Xinguo
Jiang, Wei
author_sort Zhao, Wentao
collection PubMed
description Because large numbers of artworks are preserved in museums and galleries, much work must be done to classify these works into genres, styles and artists. Recent technological advancements have enabled an increasing number of artworks to be digitized. Thus, it is necessary to teach computers to analyze (e.g., classify and annotate) art to assist people in performing such tasks. In this study, we tested 7 different models on 3 different datasets under the same experimental setup to compare their art classification performances when either using or not using transfer learning. The models were compared based on their abilities for classifying genres, styles and artists. Comparing the result with previous work shows that the model performance can be effectively improved by optimizing the model structure, and our results achieve state-of-the-art performance in all classification tasks with three datasets. In addition, we visualized the process of style and genre classification to help us understand the difficulties that computers have when tasked with classifying art. Finally, we used the trained models described above to perform similarity searches and obtained performance improvements.
format Online
Article
Text
id pubmed-7954342
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-79543422021-03-22 Compare the performance of the models in art classification Zhao, Wentao Zhou, Dalin Qiu, Xinguo Jiang, Wei PLoS One Research Article Because large numbers of artworks are preserved in museums and galleries, much work must be done to classify these works into genres, styles and artists. Recent technological advancements have enabled an increasing number of artworks to be digitized. Thus, it is necessary to teach computers to analyze (e.g., classify and annotate) art to assist people in performing such tasks. In this study, we tested 7 different models on 3 different datasets under the same experimental setup to compare their art classification performances when either using or not using transfer learning. The models were compared based on their abilities for classifying genres, styles and artists. Comparing the result with previous work shows that the model performance can be effectively improved by optimizing the model structure, and our results achieve state-of-the-art performance in all classification tasks with three datasets. In addition, we visualized the process of style and genre classification to help us understand the difficulties that computers have when tasked with classifying art. Finally, we used the trained models described above to perform similarity searches and obtained performance improvements. Public Library of Science 2021-03-12 /pmc/articles/PMC7954342/ /pubmed/33711046 http://dx.doi.org/10.1371/journal.pone.0248414 Text en © 2021 Zhao et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Zhao, Wentao
Zhou, Dalin
Qiu, Xinguo
Jiang, Wei
Compare the performance of the models in art classification
title Compare the performance of the models in art classification
title_full Compare the performance of the models in art classification
title_fullStr Compare the performance of the models in art classification
title_full_unstemmed Compare the performance of the models in art classification
title_short Compare the performance of the models in art classification
title_sort compare the performance of the models in art classification
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7954342/
https://www.ncbi.nlm.nih.gov/pubmed/33711046
http://dx.doi.org/10.1371/journal.pone.0248414
work_keys_str_mv AT zhaowentao comparetheperformanceofthemodelsinartclassification
AT zhoudalin comparetheperformanceofthemodelsinartclassification
AT qiuxinguo comparetheperformanceofthemodelsinartclassification
AT jiangwei comparetheperformanceofthemodelsinartclassification