Sciweavers

ICIP
2010
IEEE

Fast semantic scene segmentation with conditional random field

13 years 9 months ago
Fast semantic scene segmentation with conditional random field
In this paper, we present a fast approach to obtain semantic scene segmentation with high precision. We employ a two-stage classifier to label all image pixels. First, we use the regularized logistic regression to combine different appearance-based features and the improved spatial layout of labeling information. In the second stage, we incorporate the local, regional and global cues into a conditional random field model to provide a final segmentation, and a fast max-margin training method is employed to learn the parameters of the model quickly. The comparison experiments on four multiclass image segmentation databases show that our approach can achieve comparable semantic segmentation results and work faster than that of the state-of-the-art approaches.
Wen Yang, Dengxin Dai, Bill Triggs, Gui-Song Xia,
Added 12 Feb 2011
Updated 12 Feb 2011
Type Journal
Year 2010
Where ICIP
Authors Wen Yang, Dengxin Dai, Bill Triggs, Gui-Song Xia, Chu He
Comments (0)