Abstract : Regular decompositions are necessary for most superpixel-based object recognition or tracking applications. So far in the literature, the regularity or compactness of a superpixel shape is mainly measured by its circularity. In this work, we first demonstrate that such measure is not adapted for super-pixel evaluation, since it does not directly express regularity but circular appearance. Then, we propose a new metric that considers several shape regularity aspects: convexity, balanced repartition, and contour smoothness. Finally, we demonstrate that our measure is robust to scale and noise and enables to more relevantly compare superpixel methods.
https://hal.archives-ouvertes.fr/hal-01510062
Contributeur : Rémi Giraud
<>
Soumis le : samedi 20 mai 2017 - 15:40:43
Dernière modification le : jeudi 11 janvier 2018 - 06:21:23
Rémi Giraud, Vinh-Thong Ta, Nicolas Papadakis. Robust Shape Regularity Criteria for Superpixel Evaluation. IEEE International Conference on Image Processing (ICIP), Sep 2017, Beijing, China. 〈hal-01510062〉
