Evolving ambiguous images

Penousal Machado, Adriano Vinhas, João Correia, Aniko Ekárt

Research output: Chapter in Book/Published conference outputConference publication


This work explores the creation of ambiguous images, i.e., images that may induce multistable perception, by evolutionary means. Ambiguous images are created using a general purpose approach, composed of an expression-based evolutionary engine and a set of object detectors, which are trained in advance using Machine Learning techniques. Images are evolved using Genetic Programming and object detectors are used to classify them. The information gathered during classification is used to assign fitness. In a first stage, the system is used to evolve images that resemble a single object. In a second stage, the discovery of ambiguous images is promoted by combining pairs of object detectors. The analysis of the results highlights the ability of the system to evolve ambiguous images and the differences between computational and human ambiguous images.

Original languageEnglish
Title of host publicationProceedings of the twenty-fourth International Joint Conference on Artificial Intelligence (IJCAI 2015
PublisherInternational Joint Conferences on Artificial Intelligence
Number of pages7
ISBN (Print)978-1-57735-738-4
Publication statusPublished - 2015
Event24th International Joint Conference on Artificial Intelligence - Buenos Aires, Argentina
Duration: 25 Jul 201531 Jul 2015


Conference24th International Joint Conference on Artificial Intelligence
Abbreviated titleIJCAI 2015
CityBuenos Aires

Bibliographical note

Funding: Fundação para a Ciêencia e Tecnologia (FCT), Portugal (SFRH/BD/90968/2012); and European Commission 7FP (project ConCreTe, Future and
Emerging Technologies (FET) (611733).


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

Cite this