The power of computer vision: A critical analysis

Rosalie Waelen

Research output: ThesisPhD Thesis - Research UT, graduation UT

198 Downloads (Pure)


Computer vision is a subfield of artificial intelligence (AI), focused on automizing the analysis of images and videos. This dissertation offers a critical analysis of computer vision, discussing the potential ethical and societal implications of the technology. The critical analysis is based on a new approach to AI ethics, which is inspired by the tradition of critical theory.

The goal of the critical analysis of computer vision is to uncover the multitude of ways in which computer vision can impact human autonomy. Some topics discussed in light of this goal are: the history of cameras and their constitutive effects, the ways in which facial recognition tools can misrecognize people in a normative sense, and the exploitative nature of datafication practices.

The critical approach to AI ethics that is presented in this dissertation, is critical in the sense that it shares critical theory’s emancipatory aim and preoccupation with power dynamics. The critical approach consists of a framework that allows AI ethicists to identify AI’s ethical and societal implications in terms of power, and to evaluate these issues in light of their impact on human autonomy. However, the approach also encourages more direct and in-depth applications of the critical theory literature to address AI’s impact on individual lives and society. The critical analysis of computer vision functions as a case study for testing out this new, critical approach to AI ethics.
Original languageEnglish
QualificationDoctor of Philosophy
Awarding Institution
  • University of Twente
  • Brey, Philip A.E., Supervisor
  • Erden, Yasemin J., Co-Supervisor
Award date27 Sept 2023
Place of PublicationEnschede
Print ISBNs978-90-365-5793-1
Electronic ISBNs978-90-365-5794-8
Publication statusPublished - 2023


Dive into the research topics of 'The power of computer vision: A critical analysis'. Together they form a unique fingerprint.

Cite this