1 / 16

GrabCut: Interactive Foreground Extraction for Fast & Accurate Results

GrabCut is a powerful interactive tool for foreground extraction using iterated graph cuts. It efficiently separates foreground and background through user input, boundaries, and regions. By leveraging color coherence energy and optimization techniques, it achieves global minimal energy in polynomial time, ensuring precise segmentations. The color model incorporates a Gaussian mixture model, while the coherence model defines objects as coherent pixel sets. GrabCut handles both straightforward and challenging examples, such as camouflage and low-contrast images, with high accuracy and efficiency. Evaluation results show low error rates, making GrabCut a reliable solution. This tool is based on color and contrast information, making it a versatile option for various applications.

alynch
Download Presentation

GrabCut: Interactive Foreground Extraction for Fast & Accurate Results

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. GrabCutInteractive Foreground Extraction using Iterated Graph CutsCarsten RotherVladimir Kolmogorov Andrew BlakeMicrosoft Research Cambridge-UK

  2. video

  3. GrabCut – Interactive Foreground Extraction2 Problem Fast & Accurate ?

  4. GrabCut – Interactive Foreground Extraction3 What GrabCut does Magic Wand(198?) Intelligent ScissorsMortensen and Barrett (1995) GrabCut User Input Result Regions Regions & Boundary Boundary

  5. GrabCut – Interactive Foreground Extraction4 Framework Input: Image Output: Segmentation Parameters:Colour ,Coherence Energy: Optimization:

  6. Foreground (source) Min Cut Background(sink) Cut: separating source and sink; Energy: collection of edges Min Cut: Global minimal enegry in polynomial time GrabCut – Interactive Foreground Extraction5 Graph CutsBoykov and Jolly (2001) Image

  7. GrabCut – Interactive Foreground Extraction6 Iterated Graph Cut ? User Initialisation Graph cuts to infer the segmentation K-means for learning colour distributions

  8. GrabCut – Interactive Foreground Extraction7 Iterated Graph Cuts Guaranteed toconverge 1 3 4 2 Result Energy after each Iteration

  9. GrabCut – Interactive Foreground Extraction8 Colour Model Gaussian Mixture Model (typically 5-8 components) R R Iterated graph cut Foreground &Background Foreground G Background G Background

  10. Blake et al. (2004):Learn jointly GrabCut – Interactive Foreground Extraction9 Coherence Model An object is a coherent set of pixels:

  11. GrabCut – Interactive Foreground Extraction10 Moderately straightforward examples … GrabCut completes automatically

  12. GrabCut – Interactive Foreground Extraction11 Difficult Examples Camouflage & Low Contrast Fine structure No telepathy Initial Rectangle InitialResult

  13. GrabCut – Interactive Foreground Extraction12 Evaluation – Labelled Database Available online: http://research.microsoft.com/vision/cambridge/segmentation/

  14. Error Rate: 0.72% GrabCut – Interactive Foreground Extraction13 Comparison Boykov and Jolly (2001) GrabCut User Input Result Error Rate: 1.87% Error Rate: 1.81% Error Rate: 1.32% Error Rate: 1.25% Error Rate: 0.72%

  15. GrabCut – Interactive Foreground Extraction22 Summary Intelligent Scissors Mortensen and Barrett (1995) LazySnappingLi et al. (2004) Graph Cuts Boykov and Jolly (2001) Magic Wand (198?) GrabCutRother et al. (2004)

  16. GrabCut – Interactive Foreground Extraction23 Conclusions GrabCut – powerful interactive extraction tool Iterated Graph Cut based on colour and contrast Regularized alpha matting by Dynamic Programming

More Related