Image segmentation using iterated graph cuts based on multi-scale smoothing

Authors:
Tomoyuki Nagahashi;Hironobu Fujiyoshi;Takeo Kanade
Affiliations:
Dept. of Computer Science, Chubu University, Kasugai, Aichi, Japan;Dept. of Computer Science, Chubu University, Kasugai, Aichi, Japan;The Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania
Venue:
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
Year:
2007

Citing 3
Cited 3

"GrabCut": interactive foreground extraction using iterated graph cuts

ACM SIGGRAPH 2004 Papers
An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision

IEEE Transactions on Pattern Analysis and Machine Intelligence
Graph Cuts and Efficient N-D Image Segmentation

International Journal of Computer Vision

Interactive shadow removal from a single image using hierarchical graph cut

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part I
Video segmentation using iterated graph cuts based on spatio-temporal volumes

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
Panorama weaving: fast and flexible seam processing

ACM Transactions on Graphics (TOG) - SIGGRAPH 2012 Conference Proceedings

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a novel approach to image segmentation using iterated Graph Cuts based on multi-scale smoothing. We compute the prior probability obtained by the likelihood from a color histogram and a distance transform using the segmentation results from graph cuts in the previous process, and set the probability as the t-link of the graph for the next process. The proposed method can segment the regions of an object with a stepwise process from global to local segmentation by iterating the graph-cuts process with Gaussian smoothing using different values for the standard deviation. We demonstrate that we can obtain 4.7% better segmentation than that with the conventional approach.