Robust shape regularity criteria for superpixel evaluation

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 sup...

Full description

Saved in:
Bibliographic Details
Main Authors: Giraud, Remi, Ta, Vinh-Thong, Papadakis, Nicolas
Format: Conference Proceeding
Language:English
Subjects:
Compactness
Noise measurement
Quality measure
Robustness
Scalp
Shape
Shape measurement
Superpixels
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2381-8549
DOI:10.1109/ICIP.2017.8296924