"RegionCut" - Interactive Multi-Label Segmentation Utilizing Cellular Automaton
Abstract
This paper addresses the problem of interactive image segmentation. We propose an extension of the GrowCut framework which follows Cellular Automaton theory and is comparable to a label propagation algorithm. Therefore, user labels are propagated according to Cellular Automaton until convergency. A common problem of GrowCut is the time consuming user initialization which requires distributed seeds. Our main contribution focuses on determining such an initialization utilizing GMMs and spherical coordinates. Furthermore we propose a new weight function based on the mean image gradient. According to our evaluation, our extensions result in a simplified user interaction and in better results in terms of accuracy and running time. Our experiments show that our method can compete with state-of-the-art energy minimization frameworks.
Cite
Text
Arndt et al. ""RegionCut" - Interactive Multi-Label Segmentation Utilizing Cellular Automaton." IEEE/CVF Winter Conference on Applications of Computer Vision, 2013. doi:10.1109/WACV.2013.6475034Markdown
[Arndt et al. ""RegionCut" - Interactive Multi-Label Segmentation Utilizing Cellular Automaton." IEEE/CVF Winter Conference on Applications of Computer Vision, 2013.](https://mlanthology.org/wacv/2013/arndt2013wacv-regioncut/) doi:10.1109/WACV.2013.6475034BibTeX
@inproceedings{arndt2013wacv-regioncut,
title = {{"RegionCut" - Interactive Multi-Label Segmentation Utilizing Cellular Automaton}},
author = {Arndt, Oliver Jakob and Scheuermann, Björn and Rosenhahn, Bodo},
booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision},
year = {2013},
pages = {309-316},
doi = {10.1109/WACV.2013.6475034},
url = {https://mlanthology.org/wacv/2013/arndt2013wacv-regioncut/}
}