Oversegmentation Methods: A New Evaluation

Mathieu, Bérengère; Crouzil, Alain; Puel, Jean Baptiste

doi:10.1007/978-3-319-58838-4_21

Cited by 6 publications

(1 citation statement)

References 21 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Superpixel papers usually compare their proposals to classical approaches with few comparisons with newer methods, hampering the determination of the true impact of their contributions. Furthermore, recent approaches have not been included in previous benchmarks [8], [9], [14]- [16]. This work fills this gap by evaluating 20 superpixel segmentation methods among the most recently proposed and commonly used ones.…”

Section: Introductionmentioning

confidence: 99%

A survey on the state-of-the-art superpixel segmentation

Barcelos,

Falcão,

Guimarães

2023

Anais Estendidos Da XXXVI Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2023)

View full text Add to dashboard Cite

In contrast to the rapid progress of superpixel segmentation, their methods are often compared only with classical approaches. Also, the previous superpixel methods categorizations are insufficient to cover the recent literature. In addition, although the inner color similarity usually underlies superpixel methods, both color homogeneity measures have important drawbacks. In this work, we fill these gaps by providing a new taxonomy for superpixel segmentation, a new color homogeneity measure, and an extensive comparison among 20 superpixel methods. Experiments show that the proposed measure, named Similarity between Image and Reconstruction from Superpixels (SIRS), is more robust to slight color variations than Explained Variation. Using SIRS and the commonly used superpixel metrics, we evaluated 20 superpixel segmentation methods and provided insights into the different approaches based on the clustering categories in our taxonomy.

show abstract