Figure-ground segmentation by transferring window masks

Daniel Kuettel, Matthieu Guillaumin, and Vittorio Ferrari

Overview


This software implements the full segmentation pipeline of [1]. It also includes the large-scale segmentation transfer of [2]. It was developed under Linux with Matlab R2011b. There is no guarantee it will run on other configurations. It provides figure-ground segmentation for a test image as described in [1]. The implementation has also been extended for large-scale datasets as outlined in [2]. The algorithm works in a supervised setting, thus a training set with annotated figure-ground segmentations is needed.
The readme is provided with the code, but it can also be viewed separately here.

Examples

       

Downloads

Filename Description Size
matlab-1.2.1.zip segmentation transfer code, including readme 21MB
voc10.zip VOC10 segmentation challenge data set 3.2GB
horses.zip weizmann horses data set 561MB
README.txt Description of contents 8KB

References

  1. Figure-ground segmentation by transferring window masks
    Daniel Kuettel, and Vittorio Ferrari,
    In Computer Vision and Pattern Recognition (CVPR), 2012.
    [pdf]
  2. Segmentation Propagation in ImageNet
    Daniel Kuettel, Matthieu Guillaumin, and Vittorio Ferrari,
    In European Conference on Computer Vision (ECCV), 2012.
    [pdf]