Handle URI:
http://hdl.handle.net/10754/575743
Title:
Emerging images
Authors:
Mitra, Niloy J. ( 0000-0002-2597-0914 ) ; Chu, Hungkuo; Lee, Tongyee; Wolf, Lior; Yeshurun, Hezy; Cohen-Or, Daniel
Abstract:
Emergence refers to the unique human ability to aggregate information from seemingly meaningless pieces, and to perceive a whole that is meaningful. This special skill of humans can constitute an effective scheme to tell humans and machines apart. This paper presents a synthesis technique to generate images of 3D objects that are detectable by humans, but difficult for an automatic algorithm to recognize. The technique allows generating an infinite number of images with emerging figures. Our algorithm is designed so that locally the synthesized images divulge little useful information or cues to assist any segmentation or recognition procedure. Therefore, as we demonstrate, computer vision algorithms are incapable of effectively processing such images. However, when a human observer is presented with an emergence image, synthesized using an object she is familiar with, the figure emerges when observed as a whole. We can control the difficulty level of perceiving the emergence effect through a limited set of parameters. A procedure that synthesizes emergence images can be an effective tool for exploring and understanding the factors affecting computer vision techniques. © 2009 ACM.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
Association for Computing Machinery (ACM)
Journal:
ACM SIGGRAPH Asia 2009 papers on - SIGGRAPH Asia '09
Conference/Event name:
SIGGRAPH Asia 2009
Issue Date:
2009
DOI:
10.1145/1661412.1618509
Type:
Conference Paper
ISSN:
07300301
ISBN:
9781605588582
Appears in Collections:
Conference Papers; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorMitra, Niloy J.en
dc.contributor.authorChu, Hungkuoen
dc.contributor.authorLee, Tongyeeen
dc.contributor.authorWolf, Lioren
dc.contributor.authorYeshurun, Hezyen
dc.contributor.authorCohen-Or, Danielen
dc.date.accessioned2015-08-24T09:24:58Zen
dc.date.available2015-08-24T09:24:58Zen
dc.date.issued2009en
dc.identifier.isbn9781605588582en
dc.identifier.issn07300301en
dc.identifier.doi10.1145/1661412.1618509en
dc.identifier.urihttp://hdl.handle.net/10754/575743en
dc.description.abstractEmergence refers to the unique human ability to aggregate information from seemingly meaningless pieces, and to perceive a whole that is meaningful. This special skill of humans can constitute an effective scheme to tell humans and machines apart. This paper presents a synthesis technique to generate images of 3D objects that are detectable by humans, but difficult for an automatic algorithm to recognize. The technique allows generating an infinite number of images with emerging figures. Our algorithm is designed so that locally the synthesized images divulge little useful information or cues to assist any segmentation or recognition procedure. Therefore, as we demonstrate, computer vision algorithms are incapable of effectively processing such images. However, when a human observer is presented with an emergence image, synthesized using an object she is familiar with, the figure emerges when observed as a whole. We can control the difficulty level of perceiving the emergence effect through a limited set of parameters. A procedure that synthesizes emergence images can be an effective tool for exploring and understanding the factors affecting computer vision techniques. © 2009 ACM.en
dc.publisherAssociation for Computing Machinery (ACM)en
dc.titleEmerging imagesen
dc.typeConference Paperen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalACM SIGGRAPH Asia 2009 papers on - SIGGRAPH Asia '09en
dc.conference.date2009-12-19en
dc.conference.nameSIGGRAPH Asia 2009en
dc.conference.locationYokohama, Japanen
dc.contributor.institutionNational Cheng Kung University, Taiwanen
dc.contributor.institutionTel Aviv University, Israelen
kaust.authorMitra, Niloy J.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.