UTCS Artificial Intelligence
courses
talks/events
demos
people
projects
publications
software/data
labs
areas
admin
Ray-based color image segmentation (2008)
Changhai Xu
,
Yong Jae Lee
, and
Benjamin Kuipers
We propose a ray-based segmentation method for color images. A segment is represented by a centroid and evenly-distributed rays shooting out from it. First, a bottom-up low-level boundary detection process coarsely constructs candidate segments. Then, two top-down learning processes, mid-level intra-segment learning and high-level inter-segment learning, create the best segments. Segments are created sequentially until all pixels are classified. The number of segments is determined automatically. we test our method on the Berkeley Segmentation Dataset. Evaluation results show that our algorithm produces better results than those of the Normalized Cuts segmentation method.
View:
PDF
,
HTML
Citation:
In
Canadian Conference on Computer and Robot Vision
2008.
Bibtex:
@inproceedings{xu:cccrv08, title={Ray-based color image segmentation}, author={Changhai Xu and Yong Jae Lee and Benjamin Kuipers}, booktitle={Canadian Conference on Computer and Robot Vision}, url="http://www.cs.utexas.edu/users/ai-lab?xu:cccrv08", year={2008} }
People
Benjamin Kuipers
Formerly affiliated Faculty
kuipers [at] cs utexas edu
Yong Jae Lee
Ph.D. Alumni
yjlee0222 [at] mail utexas edu
Changhai Xu
Ph.D. Alumni
changhai [at] cs utexas edu
Areas of Interest
Computer Vision