Abstract Interactive Image Segmentation has attracted much attention in the vision and graphics community recently. A typical application for interactive image segmentation is foreground/background segmentation based on user specified brush labellings. The problem can be formulated within the binary Markov Random Field (MRF) framework which can be solved efficiently via graph cut [1]. However, no attempt has yet been made to handle segmentation of multiple regions using graph cuts. In this paper, we propose a multiclass interactive image segmentation algorithm based on the Potts MRF model. Following [2], this can be converted to a multiway cut problem first proposed in [2] and solved by expansion-move algorithms for approximate inference [2]. A faster algorithm is proposed in this paper for efficient solution of the multiway cut problem based on partial optimal labeling. To achieve this, we combine the one-vs-all classifier fusion framework with the expansion-move algorithm for label inference over large images. We justify our approach with both theoretical analysis and experimental validation.
Efficient Graph Cuts for Multiclass Interactive Image Segmentation
Computer Vision – ACCV 2007 ; 3 ; 134-144
Lecture Notes in Computer Science ; 4844 , 3
2007-01-01
11 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Edge Weight , Terminal Node , Markov Random Fields , Terminal Link , Markov Random Fields Model Computer Science , Image Processing and Computer Vision , Computer Imaging, Vision, Pattern Recognition and Graphics , Pattern Recognition , Artificial Intelligence (incl. Robotics) , Biometrics , Algorithm Analysis and Problem Complexity
Demonstration of Segmentation with Interactive Graph Cuts
British Library Conference Proceedings | 2001
|Graph Cuts and Efficient N-D Image Segmentation
British Library Online Contents | 2006
|A Multilevel Banded Graph Cuts Method for Fast Image Segmentation
British Library Conference Proceedings | 2005
|