z-logo
open-access-imgOpen Access
Shape-tailored local descriptors and their application to segmentation and tracking
Author(s) -
Naeemullah Khan,
Marei Algarni,
Anthony Yezzi,
Ganesh Sundaramoorthi
Publication year - 2015
Publication title -
2015 ieee conference on computer vision and pattern recognition (cvpr)
Language(s) - English
Resource type - Conference proceedings
ISSN - 1063-6919
ISBN - 978-1-4673-6964-0
DOI - 10.1109/cvpr.2015.7299014
Subject(s) - computing and processing
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.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here
Accelerating Research

Address

John Eccles House
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom