19 January 2016 Performance comparison of image feature detectors utilizing a large number of scenes
Author Affiliations +
Abstract
The availability of a large number of local invariant feature detectors has rendered the task of evaluating them an important issue in vision research. However, the maximum number of scenes utilized for performance comparison has so far been relatively small. This paper presents an evaluation framework and results based on it utilizing a large number of scenes, providing insights into the performance of local feature detectors under varying JPEG compression ratio, blur, and uniform light changes.
© 2016 SPIE and IS&T
Bruno Ferrarini, Shoaib Ehsan, Naveed Ur Rehman, Klaus D. McDonald-Maier, "Performance comparison of image feature detectors utilizing a large number of scenes," Journal of Electronic Imaging 25(1), 010501 (19 January 2016). https://doi.org/10.1117/1.JEI.25.1.010501 . Submission:
JOURNAL ARTICLE
4 PAGES


SHARE
RELATED CONTENT

Management Of Optical Developments Programs
Proceedings of SPIE (August 28 1979)
Optimal morphological representation of binary images
Proceedings of SPIE (June 01 1992)
Digital Northeast China for about 100 years RS dynamic...
Proceedings of SPIE (November 09 2004)
Band selection for recognition using moment invariants
Proceedings of SPIE (June 01 2005)
Project Rescue: challenges in responding to the unexpected
Proceedings of SPIE (December 15 2003)

Back to Top