Show simple item record

dc.contributor.authorMitra, Niloy J.
dc.contributor.authorChu, Hungkuo
dc.contributor.authorLee, Tongyee
dc.contributor.authorWolf, Lior
dc.contributor.authorYeshurun, Hezy
dc.contributor.authorCohen-Or, Daniel
dc.date.accessioned2015-08-24T09:24:58Z
dc.date.available2015-08-24T09:24:58Z
dc.date.issued2009
dc.identifier.isbn9781605588582
dc.identifier.issn07300301
dc.identifier.doi10.1145/1661412.1618509
dc.identifier.urihttp://hdl.handle.net/10754/575743
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.
dc.publisherAssociation for Computing Machinery (ACM)
dc.titleEmerging images
dc.typeConference Paper
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.contributor.departmentOffice of the VP
dc.contributor.departmentVisual Computing Center (VCC)
dc.identifier.journalACM SIGGRAPH Asia 2009 papers on - SIGGRAPH Asia '09
dc.conference.date2009-12-19
dc.conference.nameSIGGRAPH Asia 2009
dc.conference.locationYokohama, Japan
dc.contributor.institutionNational Cheng Kung University, Taiwan
dc.contributor.institutionTel Aviv University, Israel
kaust.personMitra, Niloy J.


This item appears in the following Collection(s)

Show simple item record