Figure-ground segmentation by transferring window masks
- 1 June 2012
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
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).Keywords
This publication has 32 references indexed in Scilit:
- Extracting foreground masks towards object recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Constrained parametric min-cuts for automatic object segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- A discriminatively trained, multiscale, deformable part modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Progressive search space reduction for human pose estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Scene completion using millions of photographsPublished by Association for Computing Machinery (ACM) ,2007
- A Seeded Image Segmentation Framework Unifying Graph Cuts And Random Walker Which Yields A New AlgorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Generic object recognition with boostingIeee Transactions On Pattern Analysis and Machine Intelligence, 2006
- "GrabCut"Published by Association for Computing Machinery (ACM) ,2004
- Globally optimal regions and boundaries as minimum ratio weight cyclesIeee Transactions On Pattern Analysis and Machine Intelligence, 2001