Revisiting the medial axis for planar shape decomposition

Abstract : We present a 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 prioritized processing of candidate part-cuts according to a 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. With our single computational model, we outperform even an ensemble method on several other competing models.
Type de document :
Article dans une revue
Computer Vision and Image Understanding, Elsevier, In press, pp.1-20. 〈10.1016/j.cviu.2018.10.007〉
Liste complète des métadonnées

https://hal.inria.fr/hal-01930939
Contributeur : Yannis Avrithis <>
Soumis le : jeudi 22 novembre 2018 - 13:42:38
Dernière modification le : samedi 1 décembre 2018 - 19:56:17

Identifiants

Citation

Nikos Papanelopoulos, Yannis Avrithis, Stefanos Kollias. Revisiting the medial axis for planar shape decomposition. Computer Vision and Image Understanding, Elsevier, In press, pp.1-20. 〈10.1016/j.cviu.2018.10.007〉. 〈hal-01930939〉

Partager

Métriques

Consultations de la notice

31