EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Using machine learning to distinguish between authentic and imitation Jackson Pollock poured paintings: A tile-driven approach to computer vision

Julian H Smith iD, Caleb Holt, Nickolaus H Smith, Richard P Taylor

PLOS ONE · 17.06.2024 · 19 (6) · e0302962

DOI: 10.1371/journal.pone.0302962 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, online erschienen am 17.06.2024. Verfasst von Julian H Smith und 3 weiteren Autor:innen. Beteiligte Einrichtung: Cloudsmiths LLC, Eugene, OR, United States of America. Hauptthemen laut MEDLINE: Paintings, Machine Learning. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Linde Martin Institute: https://www.lindemartin.com/, Ripple Group: https://rippleventures.co/about.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Jackson Pollock’s abstract poured paintings are celebrated for their striking aesthetic qualities. They are also among the most financially valued and imitated artworks, making them vulnerable to high-profile controversies involving Pollock-like paintings of unknown origin. Given the increased employment of artificial intelligence applications across society, we investigate whether established machine learning techniques can be adopted by the art world to help detect imitation Pollocks. The low number of images compared to typical artificial intelligence projects presents a potential limitation for art-related applications. To address this limitation, we develop a machine learning strategy involving a novel image ingestion method which decomposes the images into sets of multi-scaled tiles. Leveraging the power of transfer learning, this approach distinguishes between authentic and imitation poured artworks with an accuracy of 98.9%. The machine also uses the multi-scaled tiles to generate novel visual aids and interpretational parameters which together facilitate comparisons between the machine’s results and traditional investigations of Pollock’s artistic style.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PaintingsMachine LearningHumansArtificial IntelligenceImage Processing, Computer-Assisted

Autor:innen und Institutionen

  • Cloudsmiths LLC, Eugene, OR, United States of America.
  • LightningHolt LLC, Eugene, OR, United States of America.
  • Fractals Research LLC, Eugene, OR, United States of America.
  • Physics Department, University of Oregon, Eugene, OR, United States of America.

ORCID-Profile: Julian H Smith

Förderung

  • Linde Martin Institute: https://www.lindemartin.com/
  • Ripple Group: https://rippleventures.co/about

Zitieren

APA

Smith, J. H., Holt, C., Smith, N. H., & Taylor, R. P. (2024). Using machine learning to distinguish between authentic and imitation Jackson Pollock poured paintings: A tile-driven approach to computer vision. PLOS ONE, 19(6), e0302962. https://doi.org/10.1371/journal.pone.0302962

Vancouver

Smith JH, Holt C, Smith NH, Taylor RP. Using machine learning to distinguish between authentic and imitation Jackson Pollock poured paintings: A tile-driven approach to computer vision. PLOS ONE. 2024;19(6):e0302962. doi:10.1371/journal.pone.0302962

BibTeX
@article{Smith2024,
  author = {Smith, Julian H and Holt, Caleb and Smith, Nickolaus H and Taylor, Richard P},
  title = {Using machine learning to distinguish between authentic and imitation Jackson Pollock poured paintings: A tile-driven approach to computer vision},
  journal = {PLOS ONE},
  year = {2024},
  volume = {19},
  number = {6},
  pages = {e0302962},
  doi = {10.1371/journal.pone.0302962}
}
Kostenlos starten →