Emerging images synthesis from photographs

Mao Fong Jian; Hung Kuo Chu; Ruen Rone Lee; Chia Lun Ku; Yu-Shuen Wang; Chih Yuan Yao

doi:10.1145/2503385.2503492

Emerging images synthesis from photographs

Mao Fong Jian, Hung Kuo Chu^*, Ruen Rone Lee, Chia Lun Ku, Yu-Shuen Wang, Chih Yuan Yao

^*Corresponding author for this work

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Emergence refers to a phenomenon by which human perceives complete objects in a seemingly noisy image not by recognizing local parts of image but viewing the image as a whole. The Dalmatian dog image created by R. C. James is probably the best demonstration of emergence [Bach 2002]. It shows that local windows from the image reveal nothing but meaningless, complex and random black splats. Only when the image is viewed as a whole, a Dalmatian dog suddenly appears. The absence of meaningful information in local image parts largely hinders existing computer vision algorithms from recognizing emerging figures. Therefore, it makes the emergence an new type of CAPTCHA to tell human and machine apart.

Original language	English
Title of host publication	ACM SIGGRAPH 2013 Posters, SIGGRAPH 2013
DOIs	https://doi.org/10.1145/2503385.2503492
State	Published - 2013
Event	ACM Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH 2013 - Anaheim, CA, United States Duration: 21 Jul 2013 → 25 Jul 2013

Publication series

Name	ACM SIGGRAPH 2013 Posters, SIGGRAPH 2013

Conference

Conference	ACM Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH 2013
Country/Territory	United States
City	Anaheim, CA
Period	21/07/13 → 25/07/13

Access to Document

10.1145/2503385.2503492

Cite this

@inproceedings{0cfa959544384406844fd995cfa98bd0,

title = "Emerging images synthesis from photographs",

abstract = "Emergence refers to a phenomenon by which human perceives complete objects in a seemingly noisy image not by recognizing local parts of image but viewing the image as a whole. The Dalmatian dog image created by R. C. James is probably the best demonstration of emergence [Bach 2002]. It shows that local windows from the image reveal nothing but meaningless, complex and random black splats. Only when the image is viewed as a whole, a Dalmatian dog suddenly appears. The absence of meaningful information in local image parts largely hinders existing computer vision algorithms from recognizing emerging figures. Therefore, it makes the emergence an new type of CAPTCHA to tell human and machine apart.",

author = "Jian, {Mao Fong} and Chu, {Hung Kuo} and Lee, {Ruen Rone} and Ku, {Chia Lun} and Yu-Shuen Wang and Yao, {Chih Yuan}",

year = "2013",

doi = "10.1145/2503385.2503492",

language = "English",

isbn = "9781450323420",

series = "ACM SIGGRAPH 2013 Posters, SIGGRAPH 2013",

booktitle = "ACM SIGGRAPH 2013 Posters, SIGGRAPH 2013",

note = "ACM Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH 2013 ; Conference date: 21-07-2013 Through 25-07-2013",

}

Jian, MF, Chu, HK, Lee, RR, Ku, CL, Wang, Y-S & Yao, CY 2013, Emerging images synthesis from photographs. in ACM SIGGRAPH 2013 Posters, SIGGRAPH 2013., 97, ACM SIGGRAPH 2013 Posters, SIGGRAPH 2013, ACM Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH 2013, Anaheim, CA, United States, 21/07/13. https://doi.org/10.1145/2503385.2503492

TY - GEN

T1 - Emerging images synthesis from photographs

AU - Jian, Mao Fong

AU - Chu, Hung Kuo

AU - Lee, Ruen Rone

AU - Ku, Chia Lun

AU - Wang, Yu-Shuen

AU - Yao, Chih Yuan

PY - 2013

Y1 - 2013

N2 - Emergence refers to a phenomenon by which human perceives complete objects in a seemingly noisy image not by recognizing local parts of image but viewing the image as a whole. The Dalmatian dog image created by R. C. James is probably the best demonstration of emergence [Bach 2002]. It shows that local windows from the image reveal nothing but meaningless, complex and random black splats. Only when the image is viewed as a whole, a Dalmatian dog suddenly appears. The absence of meaningful information in local image parts largely hinders existing computer vision algorithms from recognizing emerging figures. Therefore, it makes the emergence an new type of CAPTCHA to tell human and machine apart.

AB - Emergence refers to a phenomenon by which human perceives complete objects in a seemingly noisy image not by recognizing local parts of image but viewing the image as a whole. The Dalmatian dog image created by R. C. James is probably the best demonstration of emergence [Bach 2002]. It shows that local windows from the image reveal nothing but meaningless, complex and random black splats. Only when the image is viewed as a whole, a Dalmatian dog suddenly appears. The absence of meaningful information in local image parts largely hinders existing computer vision algorithms from recognizing emerging figures. Therefore, it makes the emergence an new type of CAPTCHA to tell human and machine apart.

UR - http://www.scopus.com/inward/record.url?scp=84881586188&partnerID=8YFLogxK

U2 - 10.1145/2503385.2503492

DO - 10.1145/2503385.2503492

M3 - Conference contribution

AN - SCOPUS:84881586188

SN - 9781450323420

T3 - ACM SIGGRAPH 2013 Posters, SIGGRAPH 2013

BT - ACM SIGGRAPH 2013 Posters, SIGGRAPH 2013

T2 - ACM Special Interest Group on Computer Graphics and Interactive Techniques Conference, SIGGRAPH 2013

Y2 - 21 July 2013 through 25 July 2013

ER -

Emerging images synthesis from photographs

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this