publications

2024

1. Incremental Watershed Cuts: Interactive Segmentation Algorithm with Parallel Strategy

   Quentin Lebon, Josselin Lefèvre, Jean Cousty, and 1 more author

   2024

   Abs Bib PDF Code

   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 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 15 to 90 on both 2D and 3D images, thus improving the user experience on large images.

   @preprint{lebon2024iws_prl,
     author = {Lebon, Quentin and Lef{\`e}vre, Josselin and Cousty, Jean and Perret, Benjamin},
     title = {Incremental Watershed Cuts: Interactive Segmentation Algorithm with Parallel Strategy},
     year = {2024},
   }

2023

1. 

   Interactive Segmentation with Incremental Watershed Cuts

   Quentin Lebon, Josselin Lefèvre, Jean Cousty, and 1 more author

   In Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications, Nov 2023

   Abs Bib PDF Code

   In this article, we propose 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. We show that this algorithm fits perfectly in an interactive segmentation process by handling user interactions, seed addition or removal, in time linear 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 achieving significant speedup from 15 to 90, thus improving the user experience on large images.

   @inproceedings{lebon2023iws,
     author = {Lebon, Quentin and Lef{\`e}vre, Josselin and Cousty, Jean and Perret, Benjamin},
     editor = {Vasconcelos, Ver{\'o}nica and Domingues, In{\^e}s and Paredes, Sim{\~a}o},
     title = {Interactive Segmentation with Incremental Watershed Cuts},
     booktitle = {Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications},
     year = {2023},
     month = nov,
     publisher = {Springer Nature Switzerland},
     address = {Cham},
     pages = {189--200},
     isbn = {978-3-031-49018-7},
   }