Article Dans Une Revue Pattern Recognition Letters Année : 2024

Incremental Watershed Cuts: Interactive Segmentation Algorithm with Parallel Strategy

Résumé

In this article, we design an incremental method for computing seeded watershed cuts for interactive image segmentation. We propose an algorithm based on the hierarchical image representation called the binary partition tree to compute a seeded watershed cut. Additionally, we leverage properties of minimum spanning forests to introduce a parallel method for labeling a connected component. We show that those algorithms fits perfectly in an interactive segmentation process by handling user interactions, seed addition or removal, in linear time with respect to the number of affected pixels. Run time comparisons with several state-of-the-art interactive and non-interactive watershed methods show that the proposed method can handle user interactions much faster than previous methods with a significant speedup ranging from 10 to 60 on both 2D and 3D images, thus improving the user experience on large images.

Fichier principal
Vignette du fichier
PRL_2024_.pdf (2.25 Mo) Télécharger le fichier
Origine Publication financée par une institution
Licence

Dates et versions

hal-04536919 , version 1 (08-04-2024)
hal-04536919 , version 2 (06-01-2025)

Licence

Identifiants

Citer

Quentin Lebon, Josselin Lefèvre, Jean Cousty, Benjamin Perret. Incremental Watershed Cuts: Interactive Segmentation Algorithm with Parallel Strategy. Pattern Recognition Letters, 2024, ⟨10.1016/j.patrec.2024.12.005⟩. ⟨hal-04536919v2⟩
284 Consultations
348 Téléchargements

Altmetric

Partager

  • More