Higher-order segmentation via multicuts
Multicuts enable to conveniently represent discrete graphical models for unsupervised and supervised image segmentation, in the case of local energy functions that exhibit symmetries. The basic Potts model and natural extensions thereof to higher-order models provide a prominent class of such object...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
[2016]
|
| In: |
Computer vision and image understanding
Year: 2015, Volume: 143, Pages: 104-119 |
| ISSN: | 1090-235X |
| DOI: | 10.1016/j.cviu.2015.11.005 |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.1016/j.cviu.2015.11.005 Verlag, lizenzpflichtig, Volltext: http://www.sciencedirect.com/science/article/pii/S1077314215002490 |
| Author Notes: | Jörg Hendrik Kappes, Markus Speth, Gerhard Reinelt, Christoph Schnörr |
Search Result 1