Improving image segmentation by learning region affinities [electronic resource].
- Published
- Washington, D.C. : United States. Dept. of Energy, 2010.
Oak Ridge, Tenn. : Distributed by the Office of Scientific and Technical Information, U.S. Dept. of Energy. - Additional Creators
- Los Alamos National Laboratory, United States. Department of Energy, and United States. Department of Energy. Office of Scientific and Technical Information
Access Online
- Restrictions on Access
- Free-to-read Unrestricted online access
- Summary
- We utilize the context information of other regions in hierarchical image segmentation to learn new regions affinities. It is well known that a single choice of quantization of an image space is highly unlikely to be a common optimal quantization level for all categories. Each level of quantization has its own benefits. Therefore, we utilize the hierarchical information among different quantizations as well as spatial proximity of their regions. The proposed affinity learning takes into account higher order relations among image regions, both local and long range relations, making it robust to instabilities and errors of the original, pairwise region affinities. Once the learnt affinities are obtained, we use a standard image segmentation algorithm to get the final segmentation. Moreover, the learnt affinities can be naturally unutilized in interactive segmentation. Experimental results on Berkeley Segmentation Dataset and MSRC Object Recognition Dataset are comparable and in some aspects better than the state-of-art methods.
- Report Numbers
- E 1.99:la-ur-10-07413
E 1.99: la-ur-10-7413
la-ur-10-7413
la-ur-10-07413 - Subject(s)
- Other Subject(s)
- Note
- Published through SciTech Connect.
11/03/2010.
"la-ur-10-07413"
" la-ur-10-7413"
2011 IEEE Conference on Computer Vision & Pattern Recognition ; June 21, 2011 ; Colorado Springs, CO.
Prasad, Lakshman; Yang, Xingwei; Latecki, Longin J. - Funding Information
- AC52-06NA25396
View MARC record | catkey: 14654102