Generating Ambiguous Figure-Ground Images

Ying Miao Kuo, Hung Kuo Chu, Ming Te Chi, Ruen Rone Lee, Tong Yee Lee

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Ambiguous figure-ground images, mostly represented as binary images, are fascinating as they present viewers a visual phenomena of perceiving multiple interpretations from a single image. In one possible interpretation, the white region is seen as a foreground figure while the black region is treated as shapeless background. Such perception can reverse instantly at any moment. In this paper, we investigate the theory behind this ambiguous perception and present an automatic algorithm to generate such images. We model the problem as a binary image composition using two object contours and approach it through a three-stage pipeline. The algorithm first performs a partial shape matching to find a good partial contour matching between objects. This matching is based on a content-aware shape matching metric, which captures features of ambiguous figure-ground images. Then we combine matched contours into a compound contour using an adaptive contour deformation, followed by computing an optimal cropping window and image binarization for the compound contour that maximize the completeness of object contours in the final composition. We have tested our system using a wide range of input objects and generated a large number of convincing examples with or without user guidance. The efficiency of our system and quality of results are verified through an extensive experimental study.

Original languageEnglish
Article number7420730
Pages (from-to)1534-1545
Number of pages12
JournalIEEE Transactions on Visualization and Computer Graphics
Volume23
Issue number5
DOIs
Publication statusPublished - 2017 May 1

Fingerprint

Binary images
Chemical analysis
Pipelines

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Computer Graphics and Computer-Aided Design

Cite this

Kuo, Ying Miao ; Chu, Hung Kuo ; Chi, Ming Te ; Lee, Ruen Rone ; Lee, Tong Yee. / Generating Ambiguous Figure-Ground Images. In: IEEE Transactions on Visualization and Computer Graphics. 2017 ; Vol. 23, No. 5. pp. 1534-1545.
@article{131a3957f64a4eb2a21300bbbb379b7a,
title = "Generating Ambiguous Figure-Ground Images",
abstract = "Ambiguous figure-ground images, mostly represented as binary images, are fascinating as they present viewers a visual phenomena of perceiving multiple interpretations from a single image. In one possible interpretation, the white region is seen as a foreground figure while the black region is treated as shapeless background. Such perception can reverse instantly at any moment. In this paper, we investigate the theory behind this ambiguous perception and present an automatic algorithm to generate such images. We model the problem as a binary image composition using two object contours and approach it through a three-stage pipeline. The algorithm first performs a partial shape matching to find a good partial contour matching between objects. This matching is based on a content-aware shape matching metric, which captures features of ambiguous figure-ground images. Then we combine matched contours into a compound contour using an adaptive contour deformation, followed by computing an optimal cropping window and image binarization for the compound contour that maximize the completeness of object contours in the final composition. We have tested our system using a wide range of input objects and generated a large number of convincing examples with or without user guidance. The efficiency of our system and quality of results are verified through an extensive experimental study.",
author = "Kuo, {Ying Miao} and Chu, {Hung Kuo} and Chi, {Ming Te} and Lee, {Ruen Rone} and Lee, {Tong Yee}",
year = "2017",
month = "5",
day = "1",
doi = "10.1109/TVCG.2016.2535331",
language = "English",
volume = "23",
pages = "1534--1545",
journal = "IEEE Transactions on Visualization and Computer Graphics",
issn = "1077-2626",
publisher = "IEEE Computer Society",
number = "5",

}

Generating Ambiguous Figure-Ground Images. / Kuo, Ying Miao; Chu, Hung Kuo; Chi, Ming Te; Lee, Ruen Rone; Lee, Tong Yee.

In: IEEE Transactions on Visualization and Computer Graphics, Vol. 23, No. 5, 7420730, 01.05.2017, p. 1534-1545.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Generating Ambiguous Figure-Ground Images

AU - Kuo, Ying Miao

AU - Chu, Hung Kuo

AU - Chi, Ming Te

AU - Lee, Ruen Rone

AU - Lee, Tong Yee

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Ambiguous figure-ground images, mostly represented as binary images, are fascinating as they present viewers a visual phenomena of perceiving multiple interpretations from a single image. In one possible interpretation, the white region is seen as a foreground figure while the black region is treated as shapeless background. Such perception can reverse instantly at any moment. In this paper, we investigate the theory behind this ambiguous perception and present an automatic algorithm to generate such images. We model the problem as a binary image composition using two object contours and approach it through a three-stage pipeline. The algorithm first performs a partial shape matching to find a good partial contour matching between objects. This matching is based on a content-aware shape matching metric, which captures features of ambiguous figure-ground images. Then we combine matched contours into a compound contour using an adaptive contour deformation, followed by computing an optimal cropping window and image binarization for the compound contour that maximize the completeness of object contours in the final composition. We have tested our system using a wide range of input objects and generated a large number of convincing examples with or without user guidance. The efficiency of our system and quality of results are verified through an extensive experimental study.

AB - Ambiguous figure-ground images, mostly represented as binary images, are fascinating as they present viewers a visual phenomena of perceiving multiple interpretations from a single image. In one possible interpretation, the white region is seen as a foreground figure while the black region is treated as shapeless background. Such perception can reverse instantly at any moment. In this paper, we investigate the theory behind this ambiguous perception and present an automatic algorithm to generate such images. We model the problem as a binary image composition using two object contours and approach it through a three-stage pipeline. The algorithm first performs a partial shape matching to find a good partial contour matching between objects. This matching is based on a content-aware shape matching metric, which captures features of ambiguous figure-ground images. Then we combine matched contours into a compound contour using an adaptive contour deformation, followed by computing an optimal cropping window and image binarization for the compound contour that maximize the completeness of object contours in the final composition. We have tested our system using a wide range of input objects and generated a large number of convincing examples with or without user guidance. The efficiency of our system and quality of results are verified through an extensive experimental study.

UR - http://www.scopus.com/inward/record.url?scp=85017389477&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017389477&partnerID=8YFLogxK

U2 - 10.1109/TVCG.2016.2535331

DO - 10.1109/TVCG.2016.2535331

M3 - Article

C2 - 26930686

AN - SCOPUS:85017389477

VL - 23

SP - 1534

EP - 1545

JO - IEEE Transactions on Visualization and Computer Graphics

JF - IEEE Transactions on Visualization and Computer Graphics

SN - 1077-2626

IS - 5

M1 - 7420730

ER -