Evolving ambiguous images

Penousal Machado; Adriano Vinhas; João Correia; Aniko Ekárt

doi:10.1145/2813536.2813539

Evolving ambiguous images

Penousal Machado, Adriano Vinhas, João Correia, Aniko Ekárt

Computer Science Research Group

Universidade de Coimbra

Research output: Contribution to specialist publication or newspaper › Article

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 language	English
Pages	7-8
Number of pages	2
Volume	2
No.	1
Specialist publication	AI Matters
Publisher	ACM
DOIs	https://doi.org/10.1145/2813536.2813539
Publication status	Published - 7 Oct 2015

Access to Document

10.1145/2813536.2813539

Cite this

@misc{908310ade12d4cf89186c7d522e6d7d8,

title = "Evolving ambiguous images",

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. ",

author = "Penousal Machado and Adriano Vinhas and Jo{\~a}o Correia and Aniko Ek{\'a}rt",

year = "2015",

month = oct,

day = "7",

doi = "10.1145/2813536.2813539",

language = "English",

volume = "2",

pages = "7--8",

journal = "AI Matters",

issn = "2372-3483",

publisher = "ACM",

address = "United States",

}

TY - GEN

T1 - Evolving ambiguous images

AU - Machado, Penousal

AU - Vinhas, Adriano

AU - Correia, João

AU - Ekárt, Aniko

PY - 2015/10/7

Y1 - 2015/10/7

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=84949815032&partnerID=8YFLogxK

U2 - 10.1145/2813536.2813539

DO - 10.1145/2813536.2813539

M3 - Article

SN - 2372-3483

VL - 2

SP - 7

EP - 8

JO - AI Matters

JF - AI Matters

PB - ACM

ER -

Evolving ambiguous images

Abstract

Access to Document

Other files and links

Fingerprint

Cite this