Interactive Image Segmentation Based on Hierarchical Graph-Cut Optimization with Generic Shape Prior

Authors:
Chen Liu;Fengxia Li;Yan Zhang;Haiyang Gu
Affiliations:
The School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 100081;The School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 100081;The School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 100081;The School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China 100081
Venue:
ICIAR '09 Proceedings of the 6th International Conference on Image Analysis and Recognition
Year:
2009

Citing 12
Cited 0

Mean Shift: A Robust Approach Toward Feature Space Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
What Energy Functions Can Be Minimizedvia Graph Cuts?

IEEE Transactions on Pattern Analysis and Machine Intelligence
Lazy snapping

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

ACM SIGGRAPH 2004 Papers
OBJ CUT

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Interactive Graph Cut Based Segmentation with Shape Priors

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Dynamic Graph Cuts for Efficient Inference in Markov Random Fields

IEEE Transactions on Pattern Analysis and Machine Intelligence
Simultaneous Segmentation and Pose Estimation of Humans Using Dynamic Graph Cuts

International Journal of Computer Vision
A Comparative Study of Energy Minimization Methods for Markov Random Fields with Smoothness-Based Priors

IEEE Transactions on Pattern Analysis and Machine Intelligence
Star Shape Prior for Graph-Cut Image Segmentation

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
Image Segmentation by Branch-and-Mincut

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part IV
Markov Random Field Modeling in Image Analysis

Markov Random Field Modeling in Image Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new algorithm for interactive image segmentation is proposed. Besides the traditional appearance and gradient information, a new Generic Shape Prior (GSP) knowledge which implies the location and the shape information of the object is combined into the framework. The GSP can be further categorized into the Regional and the Contour GSP to fit the interactive application, where a hierarchical graph-cut based optimization procedure is established, for its global optimization using the regional GSP to obtain good global segmentation results, and the local one using the Contour GSP to refine boundaries of global results. Moreover, the global optimization is based on superpixels which significantly reduce the computational complexity but preserve necessary image structures; the local one only considers a subset pixels around a contour segment, they both speed up the system. Results show our method performs better on both speed and accuracy.