Generating Ambiguous Figure-Ground Images

Ying-Miao Kuo
National Tsing Hua University
Hung-Kuo Chu
National Tsing Hua University
Ming-Te Chi
National Chengchi University
Ruen-Rone Lee
National Tsing Hua University
Tong-Yee Lee
National Cheng-Kung University


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. 


An overview of our system to automatically generate an ambiguous figure-ground image using two outer contours extracted from input images. (a) The system starts by finding candidate partial contour matches based on a novel content-aware shape matching metric. (b) The matching pair with top score is selected by the system and both matched contours are adaptively deformed to share a common boundary. (c) Lastly, the system computes an optimal cropping window and image binarization to maximize the completeness of object contours in the final result.


Ambiguous figure-ground images generated using our system with or without user intervention. (a)-(g) show four image compositions using more than two objects, while (h)-(v) are eight results composed of two objects. Our system is efficient and takes less than a second to generate these visually appealing results either automatically or with simple user assistance to specify the region of interest for shape matching ((a)-(g),(l),(s),(t)). 



We thank the anonymous reviewers for their invaluable comments and suggestions; Charles Morace for proofreading. The project was supported in part by the Ministry of Science and Technol- ogy of Taiwan (102-2221-E-007-055-MY3, 103-2221-E-007-065- MY3, 104-2218-E-004-003, and 104-2221-E-006-044-MY3). 


author  = {Ying-Miao Kuo and Hung-Kuo Chu and Ming-Te Chi and Ruen-Rone Lee and Tong-Yee Lee},
title   = {Generating Ambiguous Figure-Ground Images},
journal = {IEEE Transactions on Visualization and Computer Graphics},
volume  = {23},
issue   = {5},
pages   = {1534--1545},
year    = {2016}