Shape-tailored local descriptors and their application to segmentation and tracking
Name:
Khan_Shape-Tailored_Local_Descriptors_2015_CVPR_paper.pdf
Size:
7.234Mb
Format:
PDF
Description:
Accepted Manuscript
Type
Conference PaperKAUST Department
Computer Science ProgramComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Electrical Engineering Program
Visual Computing Center (VCC)
Date
2015-10-15Online Publication Date
2015-10-15Print Publication Date
2015-06Permanent link to this record
http://hdl.handle.net/10754/580029
Metadata
Show full item recordAbstract
We propose new dense descriptors for texture segmentation. Given a region of arbitrary shape in an image, these descriptors are formed from shape-dependent scale spaces of oriented gradients. These scale spaces are defined by Poisson-like partial differential equations. A key property of our new descriptors is that they do not aggregate image data across the boundary of the region, in contrast to existing descriptors based on aggregation of oriented gradients. As an example, we show how the descriptor can be incorporated in a Mumford-Shah energy for texture segmentation. We test our method on several challenging datasets for texture segmentation and textured object tracking. Experiments indicate that our descriptors lead to more accurate segmentation than non-shape dependent descriptors and the state-of-the-art in texture segmentation.Citation
Khan, Naeemullah, Marei Algarni, Anthony Yezzi, and Ganesh Sundaramoorthi. "Shape-Tailored Local Descriptors and their Application to Segmentation and Tracking." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3890-3899. 2015Conference/Event name
IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015ae974a485f413a2113503eed53cd6c53
10.1109/CVPR.2015.7299014