Conference proceeding
Hedgehog Shape Priors for Multi-Object Segmentation
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Vol.2016-, pp.2434-2442
06/2016
DOI: 10.1109/CVPR.2016.267
Abstract
Star-convexity prior is popular for interactive single object segmentation due to its simplicity and amenability to binary graph cut optimization. We propose a more general multi-object segmentation approach. Moreover, each object can be constrained by a more descriptive shape prior, "hedgehog". Each hedgehog shape has its surface normals locally constrained by an arbitrary given vector field, e.g. gradient of the user-scribble distance transform. In contrast to star-convexity, the tightness of our normal constraint can be changed giving better control over allowed shapes. For example, looser constraints, i.e. wider cones of allowed normals, give more relaxed hedgehog shapes. On the other hand, the tightest constraint enforces skeleton consistency with the scribbles. In general, hedgehog shapes are more descriptive than a star, which is only a special case corresponding to a radial vector field and weakest tightness. Our approach has significantly more applications than standard single star-convex segmentation, e.g. in medical data we can separate multiple non-star organs with similar appearances and weak edges. Optimization is done by our modified -expansion moves shown to be submodular for multi-hedgehog shapes.
Details
- Title: Subtitle
- Hedgehog Shape Priors for Multi-Object Segmentation
- Creators
- Hossam Isack - Western UniversityOlga Veksler - Western UniversityMilan Sonka - University of IowaYuri Boykov - Western University
- Resource Type
- Conference proceeding
- Publication Details
- 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Vol.2016-, pp.2434-2442
- DOI
- 10.1109/CVPR.2016.267
- ISSN
- 1063-6919
- eISSN
- 1063-6919
- Publisher
- IEEE
- Language
- English
- Date published
- 06/2016
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Electrical and Computer Engineering; Radiation Oncology; Fraternal Order of Eagles Diabetes Research Center; Injury Prevention Research Center; Ophthalmology and Visual Sciences
- Record Identifier
- 9984186707602771
Metrics
11 Record Views