Automatic Visual Censoring

Reducing Affective Responses to Surgical Images through Stylization


Example of an image processing technique found to be effective at making surgery images look less repulsive (a lasagna dish is used as a stand-in for a surgery image).


Researchers

  • Lonni Besancon (Linköping University)
  • Amir Semmo (Hasso Plattner Institute)
  • Tobias Isenberg (Inria)
  • Pierre Dragicevic (Inria)
  • With the collaboration of surgeons (in alphabetical order): David Biau, Bruno Frachet, Virginie Pineau, El Hadi Sariali, Marc Soubeyrand, Rabah Taouachi

You can use this link to contact us.

Overview

We present the first empirical study on using color manipulation and stylization to make surgery images and videos more palatable. While aversion to such stimuli is natural, it limits many people's ability to satisfy their curiosity, educate themselves, and make informed decisions. We selected a diverse set of image processing techniques, and tested them both on surgeons and lay people. While many artistic methods were found unusable by surgeons, edge-preserving image smoothing gave good results both in terms of preserving information (as judged by surgeons) and reducing repulsiveness (as judged by lay people). Color manipulation turned out to be not as effective.

Publications

Initial conference paper:

Lonni Besançon, Amir Semmo, David Biau, Bruno Frachet, Virginie Pineau, El Hadi Sariali, Rabah Taouachi, Tobias Isenberg, Pierre Dragicevic. Reducing Affective Responses to Surgical Images through Color Manipulation and Stylization. Proceedings of the Joint Symposium on Computational Aesthetics, Sketch-Based Interfaces and Modeling, and Non-Photorealistic Animation and Rendering, Aug 2018, Victoria, Canada. pp.4:1--4:13, ⟨10.1145/3229147.3229158⟩

Extended journal article: (including experimentations with filter settings and videos, and a description of the Arkangel extension)

Lonni Besançon, Amir Semmo, David Biau, Bruno Frachet, Virginie Pineau, El Hadi Sariali, Marc Soubeyrand, Rabah Taouachi, Tobias Isenberg, Pierre Dragicevic. Reducing Affective Responses to Surgical Images and Videos Through Stylization. Computer Graphics Forum, Wiley, In press, 39.

Other papers:

Moritz Hilscher, Hendrik Tjabben, Hendrik Rätz, Amir Semmo, Lonni Besançon, Jürgen Döllner, Matthias Trapp. Service-based Analysis and Abstraction for Content Moderation of Digital Images. Graphics Interface 2021

TEDx Talk

https://www.youtube.com/watch?v=pDHomZ8FEoU

Press

Conference talks

https://www.youtube.com/watch?v=UqrqVZUI7dI

Supplementary material

  • An OSF repository containing our preregistration, experiment code, interview notes, data, and data analysis scripts is available at https://osf.io/4pfes/.

Arkangel -- A google Chrome extension

  • A prototype of the Chrome extension is available on GitHub: github.com/lonnibesancon/Arkangel. We are working on finalizing it and making it available on the Google Chrome store.