# Robust Shape Regularity Criteria for Superpixel Evaluation

arXiv: https://arxiv.org/abs/1903.07146 · HTML: https://mlsanity.com/paper/1903.07146/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2019.

## Built on by (most cited first, 1 of 1)

- [Adaptive Superpixel for Active Learning in Semantic Segmentation](https://mlsanity.com/paper/2303.16817/) (2023)

## Abstract (arXiv)

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 superpixel 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.