Generative Image Segmentation Using Random Walks with Restart

Authors:
Tae Hoon Kim;Kyoung Mu Lee;Sang Uk Lee
Affiliations:
Dept. of EECS, ASRI, Seoul National University, Seoul, Korea 151-742;Dept. of EECS, ASRI, Seoul National University, Seoul, Korea 151-742;Dept. of EECS, ASRI, Seoul National University, Seoul, Korea 151-742
Venue:
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part III
Year:
2008

Citing 0
Cited 5

Edge-preserving colorization using data-driven random walks with restart

ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
A probabilistic model for correspondence problems using random walks with restart

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part III
Transductive segmentation of textured meshes

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
Multi-object reconstruction from dynamic scenes: An object-centered approach

Computer Vision and Image Understanding
Automatic image segmentation using constraint learning and propagation

Digital Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We consider the problem of multi-label, supervised image segmentation when an initial labeling of some pixels is given. In this paper, we propose a new generative image segmentation algorithm for reliable multi-label segmentations in natural images. In contrast to most existing algorithms which focus on the inter-label discrimination, we address the problem of finding the generative model for each label. The primary advantage of our algorithm is that it produces very good segmentation results under two difficult problems: the weak boundary problem and the texture problem. Moreover, single-label image segmentation is possible. These are achieved by designing the generative model with the Random Walks with Restart (RWR). Experimental results with synthetic and natural images demonstrate the relevance and accuracy of our algorithm.