Coarse-to-Fine Segmentation with Shape-Tailored Continuum Scale Spaces
Name:
Khan_Coarse-to-Fine SegmentationWith Shape-Tailored Continuum Scale Spaces.pdf
Size:
9.083Mb
Format:
PDF
Description:
Accepted Manuscript
Type
Conference PaperKAUST Department
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) DivisionElectrical Engineering Program
Visual Computing Center (VCC)
KAUST Grant Number
OCRF-2014-CRG3-62140401Date
2017-11-09Online Publication Date
2017-11-09Print Publication Date
2017-07Permanent link to this record
http://hdl.handle.net/10754/626947
Metadata
Show full item recordAbstract
We formulate an energy for segmentation that is designed to have preference for segmenting the coarse over fine structure of the image, without smoothing across boundaries of regions. The energy is formulated by integrating a continuum of scales from a scale space computed from the heat equation within regions. We show that the energy can be optimized without computing a continuum of scales, but instead from a single scale. This makes the method computationally efficient in comparison to energies using a discrete set of scales. We apply our method to texture and motion segmentation. Experiments on benchmark datasets show that a continuum of scales leads to better segmentation accuracy over discrete scales and other competing methods.Citation
Khan N, Hong B-W, Yezzi A, Sundaramoorthi G (2017) Coarse-to-Fine Segmentation with Shape-Tailored Continuum Scale Spaces. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Available: http://dx.doi.org/10.1109/CVPR.2017.188.Sponsors
Partially funded by KAUST OCRF-2014-CRG3-62140401, NRF-2014R1A2A1A11051941, and NSF CCF-1526848.Conference/Event name
30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Additional Links
http://ieeexplore.ieee.org/document/8099671/http://openaccess.thecvf.com/content_cvpr_2017/html/Khan_Coarse-To-Fine_Segmentation_With_CVPR_2017_paper.html
ae974a485f413a2113503eed53cd6c53
10.1109/CVPR.2017.188