Emerging images

Niloy J. Mitra, Hung Kuo Chu, Tong Yee Lee, Lior Wolf, Hezy Yeshurun, Daniel Cohen-Or

Research output: Chapter in Book/Report/Conference proceedingConference contribution

53 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationProceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09
Pages163:1-163:8
Volume28
Edition5
DOIs
Publication statusPublished - 2009 Dec 1
EventACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09 - Yokohama, Japan
Duration: 2009 Dec 162009 Dec 19

Other

OtherACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09
CountryJapan
CityYokohama
Period09-12-1609-12-19

Fingerprint

Computer vision
Image processing

All Science Journal Classification (ASJC) codes

  • Computer Graphics and Computer-Aided Design

Cite this

Mitra, N. J., Chu, H. K., Lee, T. Y., Wolf, L., Yeshurun, H., & Cohen-Or, D. (2009). Emerging images. In Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09 (5 ed., Vol. 28, pp. 163:1-163:8) https://doi.org/10.1145/1661412.1618509
Mitra, Niloy J. ; Chu, Hung Kuo ; Lee, Tong Yee ; Wolf, Lior ; Yeshurun, Hezy ; Cohen-Or, Daniel. / Emerging images. Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09. Vol. 28 5. ed. 2009. pp. 163:1-163:8
@inproceedings{366f1020fd5b4dfe981b39581d62aba3,
title = "Emerging images",
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.",
author = "Mitra, {Niloy J.} and Chu, {Hung Kuo} and Lee, {Tong Yee} and Lior Wolf and Hezy Yeshurun and Daniel Cohen-Or",
year = "2009",
month = "12",
day = "1",
doi = "10.1145/1661412.1618509",
language = "English",
isbn = "9781605588582",
volume = "28",
pages = "163:1--163:8",
booktitle = "Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09",
edition = "5",

}

Mitra, NJ, Chu, HK, Lee, TY, Wolf, L, Yeshurun, H & Cohen-Or, D 2009, Emerging images. in Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09. 5 edn, vol. 28, pp. 163:1-163:8, ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09, Yokohama, Japan, 09-12-16. https://doi.org/10.1145/1661412.1618509

Emerging images. / Mitra, Niloy J.; Chu, Hung Kuo; Lee, Tong Yee; Wolf, Lior; Yeshurun, Hezy; Cohen-Or, Daniel.

Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09. Vol. 28 5. ed. 2009. p. 163:1-163:8.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Emerging images

AU - Mitra, Niloy J.

AU - Chu, Hung Kuo

AU - Lee, Tong Yee

AU - Wolf, Lior

AU - Yeshurun, Hezy

AU - Cohen-Or, Daniel

PY - 2009/12/1

Y1 - 2009/12/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=77749264880&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77749264880&partnerID=8YFLogxK

U2 - 10.1145/1661412.1618509

DO - 10.1145/1661412.1618509

M3 - Conference contribution

AN - SCOPUS:77749264880

SN - 9781605588582

VL - 28

SP - 163:1-163:8

BT - Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09

ER -

Mitra NJ, Chu HK, Lee TY, Wolf L, Yeshurun H, Cohen-Or D. Emerging images. In Proceedings of ACM SIGGRAPH Asia 2009, SIGGRAPH Asia '09. 5 ed. Vol. 28. 2009. p. 163:1-163:8 https://doi.org/10.1145/1661412.1618509