Graphics, Imaging, and Games Lab

  • Home
  • About Us
  • Contact
  • Login
Home

From the Lab

  • Benchmark
  • Projects
  • Publications
  • Image Galleries
  • Blogs
  • Lab Members
  • Prospective Students
  • Search

Global Context Descriptors for SURF and MSER Feature Descriptors

Gail Carmichael
Robert Laganière
Prosenjit Bose
Global Context Descriptors for SURF and MSER Feature Descriptors. Canadian Conference on Computer and Robot Vision (CRV), 2010.
Conference Paper

http://dx.doi.org/10.1109/CRV.2010.47

Abstract

Global context descriptors are vectors of additional information appended to an existing descriptor, and are computed as a log-polar histogram of nearby curvature values. These have been proposed in the past to make Scale Invariant Feature Transform (SIFT) matching more robust. This additional information improved matching results especially for images with repetitive features. We propose a similar global context descriptor for Speeded Up Robust Features (SURFs) and Maximally Stable Extremal Regions (MSERs). Our experiments show some improvement for SURFs when using the global context, and much improvement for MSER.


BibTeX

@INPROCEEDINGS{5479170,
author={Carmichael, G. and Laganiè andre, R. and Bose, P.},
booktitle={Computer and Robot Vision (CRV), 2010 Canadian Conference on}, title={Global Context Descriptors for SURF and MSER Feature Descriptors},
year={2010},
month=31 2010-june 2,
volume={},
number={},
pages={309 -316},
keywords={MSER feature descriptors;SURF;global context descriptors;log-polar histogram;maximally stable extremal regions;scale invariant feature transform matching;speeded up robust features;edge detection;feature extraction;image matching;},
doi={10.1109/CRV.2010.47},
ISSN={},}

  • Home
  • About Us
  • Contact
  • Login