ML Anthology

Co-Sparse Textural Similarity for Interactive Segmentation

Claudia Nieuwenhuis, Simon Hawe, Martin Kleinsteuber, Daniel Cremers
ECCV 2014 pp. 285-301
doi:10.1007/978-3-319-10599-4_19 /eccv/2014/nieuwenhuis2014eccv-co/

Abstract

We propose an algorithm for segmenting natural images based on texture and color information, which leverages the co-sparse analysis model for image segmentation. As a key ingredient of this method, we introduce a novel textural similarity measure, which builds upon the co-sparse representation of image patches. We propose a statistical MAP inference approach to merge textural similarity with information about color and location. Combined with recently developed convex multilabel optimization methods this leads to an efficient algorithm for interactive segmentation, which is easily parallelized on graphics hardware. The provided approach outperforms state-of-the-art interactive segmentation methods on the Graz Benchmark.

PDF ECCV Semantic Scholar

Cite

Text

Nieuwenhuis et al. "Co-Sparse Textural Similarity for Interactive Segmentation." European Conference on Computer Vision, 2014. doi:10.1007/978-3-319-10599-4_19

Markdown

[Nieuwenhuis et al. "Co-Sparse Textural Similarity for Interactive Segmentation." European Conference on Computer Vision, 2014.](https://mlanthology.org/eccv/2014/nieuwenhuis2014eccv-co/) doi:10.1007/978-3-319-10599-4_19

BibTeX

@inproceedings{nieuwenhuis2014eccv-co,
  title     = {{Co-Sparse Textural Similarity for Interactive Segmentation}},
  author    = {Nieuwenhuis, Claudia and Hawe, Simon and Kleinsteuber, Martin and Cremers, Daniel},
  booktitle = {European Conference on Computer Vision},
  year      = {2014},
  pages     = {285-301},
  doi       = {10.1007/978-3-319-10599-4_19},
  url       = {https://mlanthology.org/eccv/2014/nieuwenhuis2014eccv-co/}
}