English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In the superpixel literature, the comparison of state-of-the-art methods canbe biased by the non-robustness of some metrics to decomposition aspects, suchas the superpixel scale. Moreover, most recent decomposition methods allow toset a shape regularity parameter, which can have a substantial impact on themeasured performances. In this paper, we introduce an evaluation framework,that aims to unify the comparison process of superpixel methods. We investigatethe limitations of existing metrics, and propose to evaluate each of the threecore decomposition aspects: color homogeneity, respect of image objects andshape regularity. To measure the regularity aspect, we propose a new globalregularity measure (GR), which addresses the non-robustness of state-of-the-artmetrics. We evaluate recent superpixel methods with these criteria, at severalsuperpixel scales and regularity levels. The proposed framework reduces thebias in the comparison process of state-of-the-art superpixel methods. Finally,we demonstrate that the proposed GR measure is correlated with the performancesof various applications.

Evaluation Framework of Superpixel Methods with a Global Regularity Measure