 |
Conference papers
Robust Shape Regularity Criteria for Superpixel Evaluation
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.
Cited literature [22 references]
https://hal.archives-ouvertes.fr/hal-01510062
Contributor : Rémi Giraud <>
Submitted on : Saturday, May 20, 2017 - 3:40:43 PM
Last modification on : Tuesday, December 8, 2020 - 9:51:07 AM
Contributor : Rémi Giraud <>
Submitted on : Saturday, May 20, 2017 - 3:40:43 PM
Last modification on : Tuesday, December 8, 2020 - 9:51:07 AM
File
Giraud_SRC_ICIP17.pdf
Files produced by the author(s)
Licence
Distributed under a Creative Commons Attribution - NonCommercial 4.0 International License