ML Anthology

Globally Optimal Closed-Surface Segmentation for Connectomics

Björn Andres, Thorben Kröger, Kevin L. Briggman, Winfried Denk, Natalya Korogod, Graham Knott, Ullrich Köthe, Fred A. Hamprecht
ECCV 2012 pp. 778-791
doi:10.1007/978-3-642-33712-3_56 /eccv/2012/andres2012eccv-globally/

Abstract

We address the problem of partitioning a volume image into a previously unknown number of segments, based on a likelihood of merging adjacent supervoxels. Towards this goal, we adapt a higher-order probabilistic graphical model that makes the duality between supervoxels and their joint faces explicit and ensures that merging decisions are consistent and surfaces of final segments are closed. First, we propose a practical cutting-plane approach to solve the MAP inference problem to global optimality despite its NP-hardness. Second, we apply this approach to challenging large-scale 3D segmentation problems for neural circuit reconstruction (Connectomics), demonstrating the advantage of this higher-order model over independent decisions and finite-order approximations.

PDF ECCV Semantic Scholar

Cite

Text

Andres et al. "Globally Optimal Closed-Surface Segmentation for Connectomics." European Conference on Computer Vision, 2012. doi:10.1007/978-3-642-33712-3_56

Markdown

[Andres et al. "Globally Optimal Closed-Surface Segmentation for Connectomics." European Conference on Computer Vision, 2012.](https://mlanthology.org/eccv/2012/andres2012eccv-globally/) doi:10.1007/978-3-642-33712-3_56

BibTeX

@inproceedings{andres2012eccv-globally,
  title     = {{Globally Optimal Closed-Surface Segmentation for Connectomics}},
  author    = {Andres, Björn and Kröger, Thorben and Briggman, Kevin L. and Denk, Winfried and Korogod, Natalya and Knott, Graham and Köthe, Ullrich and Hamprecht, Fred A.},
  booktitle = {European Conference on Computer Vision},
  year      = {2012},
  pages     = {778-791},
  doi       = {10.1007/978-3-642-33712-3_56},
  url       = {https://mlanthology.org/eccv/2012/andres2012eccv-globally/}
}