A fast hierarchical approach to image segmentation

In this paper, we propose a hierarchical approach to image segmentation based on the use of a graph regularisation algorithm. The initial segmentation map is obtained using the normalized cut segmentation algorithm. We then refine the segmentation results by iteratively propagating the class-labels...

Full description

Saved in:
Bibliographic Details
Published in2008 19th International Conference on Pattern Recognition pp. 1 - 4
Main Authors Zhouyu Fu, Robles-Kelly, A.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2008
Subjects
Australia
Computational efficiency
Image databases
Image resolution
Image sampling
Image segmentation
Iterative algorithms
Labeling
Noise robustness
Recycling
Online AccessGet full text

Cover

More Information
Summary:In this paper, we propose a hierarchical approach to image segmentation based on the use of a graph regularisation algorithm. The initial segmentation map is obtained using the normalized cut segmentation algorithm. We then refine the segmentation results by iteratively propagating the class-labels from coarse-to-fine sampling levels. Image segmentation at each intermediate level is recast as a constrained graph regularisation problem that can be solved efficiently. The multi-level nature of our method achieves low computational cost and robustness to noise corruption. We provide experimental results on the Berkeley Image Database and show the efficacy of our method for segmentation of high resolution images.
ISBN:9781424421749
1424421748
ISSN:1051-4651
2831-7475
DOI:10.1109/ICPR.2008.4761590