Abstract / Description of output
We present a novel technique for figure-ground segmentation, where the goal is to separate all foreground objects in a test image from the background. We decompose the test image and all images in a supervised training set into overlapping windows likely to cover foreground objects. The key idea is to transfer segmentation masks from training windows that are visually similar to windows in the test image. These transferred masks are then used to derive the unary potentials of a binary, pairwise energy function defined over the pixels of the test image, which is minimized with standard graph-cuts. This results in a fully automatic segmentation scheme, as opposed to interactive techniques based on similar energy functions. Using windows as support regions for transfer efficiently exploits the training data, as the test image does not need to be globally similar to a training image for the method to work. This enables to compose novel scenes using local parts of training images. Our approach obtains very competitive results on three datasets (PASCAL VOC 2010 segmentation challenge, Weizmann horses, Graz-02).
Original language | English |
---|---|
Title of host publication | Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on |
Pages | 558-565 |
Number of pages | 8 |
ISBN (Electronic) | 978-1-4673-1227-1 |
DOIs | |
Publication status | Published - 1 Jun 2012 |
Keywords / Materials (for Non-textual outputs)
- graph theory
- image segmentation
- masks
- Graz-02
- PASCAL VOC 2010 segmentation challenge
- Weizmann horses
- automatic segmentation scheme
- binary energy function
- figure-ground segmentation
- foreground objects
- interactive techniques
- overlapping windows
- pairwise energy function
- segmentation masks transfer
- similar energy functions
- standard graph-cuts
- supervised training set
- support regions
- test image
- training data
- training image
- transferred masks
- transferring window masks
- unary potentials
- Computational modeling
- Image segmentation
- Labeling
- Minimization
- Pipelines
- Training
- Training data