How to scale hyperparameters for quickshift image segmentation - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

How to scale hyperparameters for quickshift image segmentation

Résumé

Quickshift is a popular algorithm for image segmentation, used as a preprocessing step in many applications. Unfortunately, it is quite challenging to understand the hyperparameters' influence on the number and shape of superpixels produced by the method. In this paper, we study theoretically a slightly modified version of the quickshift algorithm, with a particular emphasis on homogeneous image patches with i.i.d. pixel noise and sharp boundaries between such patches. Leveraging this analysis, we derive a simple heuristic to scale quickshift hyperparameters with respect to the image size, which we check empirically.

Dates et versions

hal-03842452 , version 1 (07-11-2022)

Identifiants

Citer

Damien Garreau. How to scale hyperparameters for quickshift image segmentation. 2022. ⟨hal-03842452⟩
16 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More