1 / 1

Geodesic Star Convexity for interactive image segmentation

Geodesic Star Convexity for interactive image segmentation. Varun Gulshan † , Carsten Rother ‡ , Antonio Criminisi ‡ , Andrew Blake ‡ and Andrew Zisserman †. † Visual Geometry Group, University of Oxford, UK ‡ Microsoft Research, Cambridge, UK. c. 1. Star-convexity.

magda
Télécharger la présentation

Geodesic Star Convexity for interactive image segmentation

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Geodesic Star Convexity for interactive image segmentation VarunGulshan†, Carsten Rother‡, Antonio Criminisi‡, Andrew Blake‡ and Andrew Zisserman† †Visual Geometry Group, University of Oxford, UK ‡Microsoft Research, Cambridge, UK c 1. Star-convexity 2. Star-convexity -- Extensions 3. Visibility Experiment New Brush Stroke 2.1 Multiple Stars 2.2 Geodesic Stars Let y denote a binary segmentation and S*({c}) the set of star convex shapes wrt to center c. Star-convex constraint expressed as an energy: c q Semantics I – visibility to atleast one center (equivalently: union of star shape sets) p Factorization into pairwise terms: • The union constraint is not submodular. • Semantics don’t extend easily to brush strokes as star centers • Energy is submodular as (1,0) labeling has infinite energy. • Only needs to be imposed for neighbouring pixels – hence efficient. Geodesic Euclidean Veksler, ECCV 08 [1] Occlusion rates Semantics II – visibility to nearest star center • Tractable to implement (submodular) • Semantics extend nicely to brush strokes as star centers Visualization of geodesics computed using image gradients 4. Star-convexity in an interactive system 5. Evaluation BG stroke Simulated user [2] Boykov Jolly Energy: .... FG stroke BG stroke Original image User interaction Dataset: 151 Images taken from GrabCut, PASCAL VOC and the alpha matting dataset. Evaluation criteria: Measure avg. number of strokes to reach desired accuracy. FG stroke GSC Dij-GC [5] BJ Original image User interaction Color likelihood 4.1 Sequential system Code and dataset available at: http://www.robots.ox.ac.uk/~vgg/research/iseg/ Output - BJ Output - GSC SP = Shortest Paths [4] RW = Random Walker [3] PP = Post-Processing for connected components Comparison: Various shape constraints Comparison: Different algorithms [1] O. Veksler. Star shape prior for graph-cut based image segmentation. ECCV, 2008 [2] H. Nickisch, P. Kohli and C. Rother. Learning an interactive segmentation system. arXiv Technical Report, Dec. 2009. [3] L. Grady. Random walks for image segmentation. IEEE PAMI, 2006 [4] X. Bai and G. Sapiro. Geodesic matting: A framework for fast interactive image and video segmentation and matting. IJCV 2009 [5] S. Vicente, V. Kolmogorov and C. Rother. Graph cut based image segmentation with connectivity priors. CVPR 2008. References

More Related