Affine invariant Harris-Bessel interest point detector
Affine invariant Harris-Bessel interest point detector
An affine invariant interest point detector named here as Harris-Bessel detector employing Bessel filters is proposed in this paper. The Harris-Bessel detector is applied on the images a well-known database in the literature. Our numerical results indicate that this detector is competitive and has better repeatability and localization measures than those of the affine invariant Harris-Laplace interest point detector. We also numerically demonstrate in this paper that the Harris-Bessel detector is affine invariant and is in average 450 times faster than the affine invariant Harris-Laplace detector for the images of the database.
367-375
Mahmoodi, Sasan
91ca8da4-95dc-4c1e-ac0e-f2c08d6ac7cf
Saba, Nasim
d53a301a-db19-47f0-a346-6b6a635e01c1
2014
Mahmoodi, Sasan
91ca8da4-95dc-4c1e-ac0e-f2c08d6ac7cf
Saba, Nasim
d53a301a-db19-47f0-a346-6b6a635e01c1
Mahmoodi, Sasan and Saba, Nasim
(2014)
Affine invariant Harris-Bessel interest point detector.
Advances in Visual Computing.
.
(doi:10.1007/978-3-319-14364-4_35).
Record type:
Conference or Workshop Item
(Paper)
Abstract
An affine invariant interest point detector named here as Harris-Bessel detector employing Bessel filters is proposed in this paper. The Harris-Bessel detector is applied on the images a well-known database in the literature. Our numerical results indicate that this detector is competitive and has better repeatability and localization measures than those of the affine invariant Harris-Laplace interest point detector. We also numerically demonstrate in this paper that the Harris-Bessel detector is affine invariant and is in average 450 times faster than the affine invariant Harris-Laplace detector for the images of the database.
This record has no associated files available for download.
More information
Published date: 2014
Venue - Dates:
Advances in Visual Computing, 2014-01-01
Organisations:
Vision, Learning and Control
Identifiers
Local EPrints ID: 369923
URI: http://eprints.soton.ac.uk/id/eprint/369923
PURE UUID: 969a081d-071b-40bd-965a-7315a47ddad3
Catalogue record
Date deposited: 08 Oct 2014 15:53
Last modified: 14 Mar 2024 18:10
Export record
Altmetrics
Contributors
Author:
Sasan Mahmoodi
Author:
Nasim Saba
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics