Evolving ambiguous images

Penousal Machado, Adriano Vinhas, João Correia, Aniko Ekárt

Research output: Contribution to specialist publicationArticle

Abstract

This article describes the use of evolutionary methods to generate ambiguous images---images that the brain or a computer may interpret in multiple ways. Object detectors often falsely identify the presence of objects in these images, even when they are not visible to human observers.
Original languageEnglish
Pages7-8
Number of pages2
Volume2
No.1
Specialist publicationAI Matters
PublisherACM
DOIs
Publication statusPublished - 7 Oct 2015

Fingerprint Dive into the research topics of 'Evolving ambiguous images'. Together they form a unique fingerprint.

  • Cite this

    Machado, P., Vinhas, A., Correia, J., & Ekárt, A. (2015). Evolving ambiguous images. AI Matters, 2(1), 7-8. https://doi.org/10.1145/2813536.2813539