EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AI Images vs. Real Photographs: Investigating Visual Recognition and Perception

Veslava Osińska iD, Weronika Kortas iD, Adam Szalach iD, Marc Welter

Journal of Eye Movement Research · 03.11.2025 · 18 (6) · 61

DOI: 10.3390/jemr18060061 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Eye Movement Research, online erschienen am 03.11.2025. Verfasst von Veslava Osińska und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Information and Communication Research, Nicolaus Copernicus University, 87-100 Toruń, Poland. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Centre, EU Horizon 2020 Research and Innovation Programme.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recently, the photorealism of generated images has improved noticeably due to the development of AI algorithms. These are high-resolution images of human faces and bodies, cats and dogs, vehicles, and other categories of objects that the untrained eye cannot distinguish from authentic photographs. The study assessed how people perceive 12 pictures generated by AI vs. 12 real photographs. Six main categories of stimuli were selected: architecture, art, faces, cars, landscapes, and pets. The visual perception of selected images was studied by means of eye tracking and gaze patterns as well as time characteristics, compared with consideration to the respondent groups’ gender and knowledge of AI graphics. After the experiment, the study participants analysed the pictures again in order to describe the reasons for their choice. The results show that AI images of pets and real photographs of architecture were the easiest to identify. The largest differences in visual perception are between men and women as well as between those experienced in digital graphics (including AI images) and the rest. Based on the analysis, several recommendations are suggested for AI developers and end-users.

Schlagwörter

Stichwörter der Autor:innen

AI imagesChatGPTGAN graphicseye trackingvisual perception

Autor:innen und Institutionen

  • Institute of Information and Communication Research, Nicolaus Copernicus University, 87-100 Toruń, Poland.
  • Institute of Informatics, College of Social and Media Culture, 87-100 Toruń, Poland.
  • Inria Center at the University of Bordeaux, 33405 Talence Cedex, France.
  • LaBRI-Laboratoire Bordelais de Recherche en Informatique, 33405 Talence Cedex, France.

ORCID-Profile: Veslava Osińska, Weronika Kortas, Adam Szalach

Förderung

  • National Science Centre
  • EU Horizon 2020 Research and Innovation Programme

Zitieren

APA

Osińska, V., Kortas, W., Szalach, A., & Welter, M. (2025). AI Images vs. Real Photographs: Investigating Visual Recognition and Perception. Journal of Eye Movement Research, 18(6), 61. https://doi.org/10.3390/jemr18060061

Vancouver

Osińska V, Kortas W, Szalach A, Welter M. AI Images vs. Real Photographs: Investigating Visual Recognition and Perception. Journal of Eye Movement Research. 2025;18(6):61. doi:10.3390/jemr18060061

BibTeX
@article{Osiska2025,
  author = {Osińska, Veslava and Kortas, Weronika and Szalach, Adam and Welter, Marc},
  title = {AI Images vs. Real Photographs: Investigating Visual Recognition and Perception},
  journal = {Journal of Eye Movement Research},
  year = {2025},
  volume = {18},
  number = {6},
  pages = {61},
  doi = {10.3390/jemr18060061}
}
Kostenlos starten →