Interactive Foreground Extraction: Using Graph Cut
Carsten Rother, Vladimir Kolmogorov, Yuri Boykov, Andrew Blake · The MIT Press eBooks · 2011
Note, this is an extended version of chapter 7 from the book:Markov Random Fields for Vision and Image Processing, MIT Press [6].In this Technical Report, references to other chapters are with respect to the book.The differences are, a new section 4.3 and extra details in section 3.2 and 3.3The topic of interactive image segmentation has received considerable attention inthe computer vision community in the last decade. Today, this topic is very mature andcommercial products exist which feature advanced research solutions. This means thatinteractive image segmentation is today probablyone of the most used computer visiontechnologies world-wide. In this chapter we review one class of interactive segmen-tation techniques, which use discrete optimization and a regional selection interface.We begin the chapter by explaining the seminal work of Boykov and Jolly [9]. Afterthat the GrabCuttechnique [36] is introduced, which improves on [9]. GrabCutis theunderlying algorithm for the Background Removal tool in the Microsoft Office 2010product. In the third part of the chapter many interesting features and details are ex-plained which are part of the product. In this process several recent research articlesare reviewed. Finally, the BackgroundRemoval tool, as well as [9, 36], are evaluatedindifferent ways on publicly available databases. This includes static and dynamic userinputs.