Shape-tailored local descriptors and their application to segmentation and tracking

Naeemullah Khan, Marei Saeed Mohammed Algarni, Anthony Yezzi, Ganesh Sundaramoorthi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations

Abstract

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.
Original languageEnglish (US)
Title of host publication2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages3890-3899
Number of pages10
ISBN (Print)9781467369640
DOIs
StatePublished - Oct 15 2015

Fingerprint

Dive into the research topics of 'Shape-tailored local descriptors and their application to segmentation and tracking'. Together they form a unique fingerprint.

Cite this