Interactive visual object extraction based on belief propagation

Authors:
Shiming Xiang;Feiping Nie;Changshui Zhang;Chunxia Zhang
Affiliations:
State Key Laboratory of Intelligent Technology and Systems, Department of Automation, Tsinghua University, Beijing, China;State Key Laboratory of Intelligent Technology and Systems, Department of Automation, Tsinghua University, Beijing, China;State Key Laboratory of Intelligent Technology and Systems, Department of Automation, Tsinghua University, Beijing, China;School of Computer Science, Software School, Beijing Institute of Technology, Beijing, China
Venue:
MMM'07 Proceedings of the 13th international conference on Multimedia Modeling - Volume Part I
Year:
2007

Citing 7
Cited 0

Fast texture synthesis using tree-structured vector quantization

Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Color Transfer between Images

IEEE Computer Graphics and Applications
Lazy snapping

ACM SIGGRAPH 2004 Papers
"GrabCut": interactive foreground extraction using iterated graph cuts

ACM SIGGRAPH 2004 Papers
Image completion with structure propagation

ACM SIGGRAPH 2005 Papers
An Iterative Optimization Approach for Unified Image Segmentation and Matting

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
On the optimality of solutions of the max-product belief-propagation algorithm in arbitrary graphs

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.01

Visualization

Abstract

Interactive foreground/background segmentation in a static image is a hot topic in image processing. Classical frameworks focus on providing one class label for the user to specify the foreground. This may be not enough in image editing. In this paper, we develop an interactive framework which can allow the user to label multiply foreground objects of interest. Our framework is constructed on belief propagation. The messages about the foreground objects and background are propagated between pixel grids. Finally, each pixel is assigned a class label after finishing the message propagation. Experimental results illustrate the validity of our method. In addition, some applications in color transfer, image completion and motion detection are given in this paper.