GrabCut

GrabCut: interactive foreground extraction using iterated graph cuts. The problem of efficient, interactive foreground/background segmentation in still images is of great practical importance in image editing. Classical image segmentation tools use either texture (colour) information, e.g. Magic Wand, or edge (contrast) information, e.g. Intelligent Scissors. Recently, an approach based on optimization by graph-cut has been developed which successfully combines both types of information. In this paper we extend the graph-cut approach in three respects. First, we have developed a more powerful, iterative version of the optimisation. Secondly, the power of the iterative algorithm is used to simplify substantially the user interaction needed for a given quality of result. Thirdly, a robust algorithm for ”border matting” has been developed to estimate simultaneously the alpha-matte around an object boundary and the colours of foreground pixels. We show that for moderately difficult examples the proposed method outperforms competitive tools.


References in zbMATH (referenced in 80 articles )

Showing results 1 to 20 of 80.
Sorted by year (citations)

1 2 3 4 next

  1. Fercoq, Olivier; Richtárik, Peter: Optimization in high dimensions via accelerated, parallel, and proximal coordinate descent (2016)
  2. Toutain, Matthieu; Elmoataz, Abderrahim; Lozes, François; Mansouri, Alamin: Non-local discrete $\infty $-Poisson and Hamilton Jacobi equations. From stochastic game to generalized distances on images, meshes, and point clouds (2016)
  3. Wu, Weiwei; Zhou, Zhuhuang; Wu, Shuicai; Zhang, Yanhua: Automatic liver segmentation on volumetric CT images using supervoxel-based graph cuts (2016)
  4. Charles, James; Pfister, Tomas; Everingham, Mark; Zisserman, Andrew: Automatic and efficient human pose estimation for sign language videos (2014)
  5. Eslami, S.M.Ali; Heess, Nicolas; Williams, Christopher K.I.; Winn, John: The shape Boltzmann machine: a strong model of object shape (2014)
  6. Guillaumin, Matthieu; Küttel, Daniel; Ferrari, Vittorio: ImageNet auto-annotation with segmentation propagation (2014)
  7. Haines, Tom S.F.; Xiang, Tao: Active rare class discovery and classification using Dirichlet processes (2014)
  8. Jung, Cheolkon; Jian, Meng; Liu, Juan; Jiao, Licheng; Shen, Yanbo: Interactive image segmentation via kernel propagation (2014)
  9. Samko, Oksana; Lai, Yu-Kun; Marshall, David; Rosin, Paul L.: Virtual unrolling and information recovery from scanned scrolled historical documents (2014)
  10. Vineet, Vibhav; Warrell, Jonathan; Torr, Philip H.S.: Filter-based mean-field inference for random fields with higher-order terms and product label-spaces (2014)
  11. Park, Sang Hyun; Lee, Soochahn; Yun, Il Dong; Lee, Sang Uk: Hierarchical MRF of globally consistent localized classifiers for 3D medical image segmentation (2013)
  12. Wang, Nan; Ai, Hai-Zhou; Tang, Feng: Who blocks who: simultaneous segmentation of occluded objects (2013)
  13. Andriluka, Mykhaylo; Roth, Stefan; Schiele, Bernt: Discriminative appearance models for pictorial structures (2012)
  14. Chen, Mingang; Sui, Bocong; Gao, Yan; Ma, Lizhuang: Efficient video cutout based on adaptive multilevel banded method (2012)
  15. Chen, S.Y.; Tong, Hanyang; Cattani, Carlo: Markov models for image labeling (2012)
  16. Damen, Dima; Hogg, David: Explaining activities as consistent groups of events (2012)
  17. Delong, Andrew; Osokin, Anton; Isack, Hossam N.; Boykov, Yuri: Fast approximate energy minimization with label costs (2012)
  18. Deselaers, Thomas; Alexe, Bogdan; Ferrari, Vittorio: Weakly supervised localization and learning with generic knowledge (2012)
  19. Eichner, M.; Marin-Jimenez, M.; Zisserman, A.; Ferrari, V.: 2D articulated human pose estimation and retrieval in (almost) unconstrained still images (2012)
  20. Ge, Qi; Xiao, Liang; Zhang, Jun; Wei, Zhi Hui: An improved region-based model with local statistical features for image segmentation (2012)

1 2 3 4 next