# Evaluation Framework of Superpixel Methods with a Global Regularity Measure

## TL;DR

This paper introduces a comprehensive evaluation framework for superpixel methods, addressing biases in existing metrics by proposing a new global regularity measure and assessing multiple decomposition aspects across various scales and regularity levels.

## Contribution

It presents a unified evaluation framework that includes a novel global regularity measure, improving the fairness and robustness of superpixel method comparisons.

## Key findings

- The new global regularity measure (GR) correlates with application performance.
- The framework reduces bias in superpixel method evaluation.
- Evaluation across multiple scales and regularity levels provides comprehensive insights.

## Abstract

In the superpixel literature, the comparison of state-of-the-art methods can be biased by the non-robustness of some metrics to decomposition aspects, such as the superpixel scale. Moreover, most recent decomposition methods allow to set a shape regularity parameter, which can have a substantial impact on the measured performances. In this paper, we introduce an evaluation framework, that aims to unify the comparison process of superpixel methods. We investigate the limitations of existing metrics, and propose to evaluate each of the three core decomposition aspects: color homogeneity, respect of image objects and shape regularity. To measure the regularity aspect, we propose a new global regularity measure (GR), which addresses the non-robustness of state-of-the-art metrics. We evaluate recent superpixel methods with these criteria, at several superpixel scales and regularity levels. The proposed framework reduces the bias in the comparison process of state-of-the-art superpixel methods. Finally, we demonstrate that the proposed GR measure is correlated with the performances of various applications.