geodesic star convexity for interactive image segmentation
DESCRIPTION
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. - PowerPoint PPT PresentationTRANSCRIPT
Geodesic Star Convexity for interactive image segmentationVarun Gulshan†, Carsten Rother‡, Antonio Criminisi‡, Andrew Blake‡ and Andrew Zisserman†
1. Star-convexity
†Visual Geometry Group, University of Oxford, UK ‡Microsoft Research, Cambridge, UK
References
p
cq
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:
Factorization into pairwise terms:
2. Star-convexity -- Extensions
Semantics I – visibility to atleast one center(equivalently: union of star shape sets)
Semantics II – visibility to nearest star center
3. Visibility Experiment
Method 1 star 2 stars
ESC 4.50±0.58 2.85±0.39
GSC 4.16±0.54 2.22±0.30
4. Star-convexity in an interactive system
Boykov Jolly Energy:
5. Evaluation
Simulated user [2]
Dataset: 151 Images taken from GrabCut, PASCAL VOC and the alpha matting dataset.
•Energy is submodular as (1,0) labeling has infinite energy.•Only needs to be imposed for neighbouring
pixels – hence efficient.
c
•The union constraint is not submodular.• Semantics don’t extend easily to
brush strokes as star centers
•Tractable to implement (submodular)• Semantics extend nicely to brush
strokes as star centers
User interaction Color likelihood
Output - BJ Output - GSC
Evaluation criteria:Measure avg. number of strokes to reach desired accuracy.
Method Avg. Effort
BJ 12.35
PP 10.66
ESC 10.57
GSC 10.23
GSCseq 9.63
Method Avg. Effort
SP 15.14
BJ 12.35
RW 12.31
GSCseq 9.63
[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.
Euclidean Geodesic
2.1 Multiple Stars 2.2 Geodesic Stars
GSC
New Brush Stroke
....
Comparison: Various shape constraints Comparison: Different algorithms
Dij-GC [5]BJ
4.1 Sequential system
Occlusion rates
Veksler, ECCV 08 [1]
Visualization of geodesics computed using image gradients
Original imageFG stroke
BG stroke User interactionOriginal image
FG stroke
BG stroke
SP = Shortest Paths [4]RW = Random Walker [3]PP = Post-Processing for
connected components
Code and dataset available at: http://www.robots.ox.ac.uk/~vgg/research/iseg/