GrabCut Interactive Foreground Extraction using Iterated Graph Cuts Carsten Rother Vladimir Kolmogorov Andrew Blake Microsoft Research Cambridge-UK Welcome. I will present Grabcut – an Interactive tool for foreground extraction.

Were are not quite there yet – but this is our system Were are not quite there yet – but this is our system. A college of mine english game of croquet. And make the task of playing the ball through the gate a bit simpler. video

Problem Fast & Accurate ? State the problem. Image object to extract and simple tool which gives high quality results with an alpha matte and even works for the case of camoflage. GrabCut – Interactive Foreground Extraction 2

Intelligent Scissors Mortensen and Barrett (1995) What GrabCut does Magic Wand (198?) Intelligent Scissors Mortensen and Barrett (1995) GrabCut User Input Result Basic idea is to combine the information which was used in the 2 well known tools: MW and IS. MS select a region of similar colour according to your input. Fat pen and the boundary snapps to high contrast edges. Grabcut combines it. And this allows us to simplify the user interface considerably by … Regions Boundary Regions & Boundary GrabCut – Interactive Foreground Extraction 3

Framework Input: Image Output: Segmentation Parameters: Colour ,Coherence Energy: Optimization: Let us phrase this segmentation task in a theoretical framework. We will phrase the segmentation problem as an energy minimization problem. Minimum energy corresponds to maximum probability of a Gibbs distribution. Eventually also over lambda. Boils down to GrabCut – Interactive Foreground Extraction 4

Graph Cuts Boykov and Jolly (2001) Foreground (source) Image Min Cut Cut: separating source and sink; Energy: collection of edges Min Cut: Global minimal enegry in polynomial time Optimization engine we use Graph Cuts. By know everybody should know what graph cut is. IN case you missed it here is a very brief introduction. To image. 3D view. First task to construct a graph. All pixels on a certain scanline. Just a few of them. Next step introduce artificial nodes. fgd and background. Edges – contrast. Boundary is quite likely between black and white. Min Cut - Minimum edge strength. Background (sink) GrabCut – Interactive Foreground Extraction 5

? Iterated Graph Cut User Initialisation We extended there work in the following way. IGC – Technique like EM – switch between 2 optimization problems. GC does not consider all other parameters. Init by user. Graph cuts to infer the segmentation K-means for learning colour distributions GrabCut – Interactive Foreground Extraction 6

Guaranteed to converge Iterated Graph Cuts Guaranteed to converge Iterations are not shown to the user; Converges: proof in the paper. 1 2 3 4 Result Energy after each Iteration GrabCut – Interactive Foreground Extraction 7

Colour Model R R G G Gaussian Mixture Model (typically 5-8 components) Iterated graph cut Foreground & Background Foreground Color enbergy. Iterations have the effect of pulling them away; D is – log likelyhood of the GMM. Background G Background G Gaussian Mixture Model (typically 5-8 components) GrabCut – Interactive Foreground Extraction 8

Coherence Model An object is a coherent set of pixels: Also coherent model. Strength of contrast – colour difference. Lambda importance of coherence model. Blake et al. (2004): Learn jointly GrabCut – Interactive Foreground Extraction 9

Moderately straightforward examples Moderately straightforward examples- after the user input automnatically … GrabCut completes automatically GrabCut – Interactive Foreground Extraction 10

Difficult Examples Camouflage & Low Contrast Fine structure No telepathy Initial Rectangle Initial Result You might wonder when does it fail. 4 cases. Low contrats – an edge not good visible GrabCut – Interactive Foreground Extraction 11

Evaluation – Labelled Database Labeled data base 70 images . availoable online. Different scenarios – simple and ifficult shapes and colour. Available online: http://research.microsoft.com/vision/cambridge/segmentation/ GrabCut – Interactive Foreground Extraction 12

Comparison Boykov and Jolly (2001) GrabCut Error Rate: 0.72% User Input Error Rate: 0.72% Databsed used to compare to BJ. Re-implented their method. Simpler same error rate Result Error Rate: 0.72% Error Rate: 1.32% Error Rate: 1.87% Error Rate: 1.81% Error Rate: 1.25% GrabCut – Interactive Foreground Extraction 13

Summary Finally – number of tools: certain scenarios. what does the user want to do for segmentation – Graph Cut – user input reduced and quality increases. Magic Wand (198?) Intelligent Scissors Mortensen and Barrett (1995) Graph Cuts Boykov and Jolly (2001) LazySnapping Li et al. (2004) GrabCut Rother et al. (2004) GrabCut – Interactive Foreground Extraction 22

Conclusions GrabCut – powerful interactive extraction tool Iterated Graph Cut based on colour and contrast Regularized alpha matting by Dynamic Programming GrabCut – Interactive Foreground Extraction 23