Planar shape decomposition made simple
Nikos Papanelopoulos and Yannis Avrithis
Abstract
We present a very simple computational model for planar shape decomposition that naturally captures most of the rules and salience measures suggested by psychophysical studies, including the minima and short-cut rules, convexity, and symmetry. It is based on a medial axis representation in ways that have not been explored before and sheds more light into the connection between existing rules like minima and convexity. In particular, vertices of the exterior medial axis directly provide the position and extent of negative minima of curvature, while a traversal of the interior medial axis directly provides a small set of candidate endpoints for part-cuts. The final selection follows a simple local convexity rule that can incorporate arbitrary salience measures. Neither global optimization nor differentiation is involved. We provide qualitative and quantitative evaluation and comparisons on ground-truth data from psychophysical experiments.
Session
Poster 1
Files
Extended Abstract (PDF, 61K)
Paper (PDF, 7M)
DOI
10.5244/C.29.13
https://dx.doi.org/10.5244/C.29.13
Citation
Nikos Papanelopoulos and Yannis Avrithis. Planar shape decomposition made simple. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 13.1-13.12. BMVA Press, September 2015.
Bibtex
@inproceedings{BMVC2015_13,
title={Planar shape decomposition made simple},
author={Nikos Papanelopoulos and Yannis Avrithis},
year={2015},
month={September},
pages={13.1-13.12},
articleno={13},
numpages={12},
booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
publisher={BMVA Press},
editor={Xianghua Xie, Mark W. Jones, and Gary K. L. Tam},
doi={10.5244/C.29.13},
isbn={1-901725-53-7},
url={https://dx.doi.org/10.5244/C.29.13}
}