Geometric and photometric invariant distinctive regions detection

Shao, Ling, Kadir, Timor and Brady, Michael (2007) Geometric and photometric invariant distinctive regions detection. Information Sciences, 177 (4). pp. 1088-1122. ISSN 0020-0255

Full text not available from this repository. (Request a copy)
Official URL: http://dx.doi.org/10.1016/j.ins.2006.09.003

Abstract

In this paper, we present a number of enhancements to the Kadir/Brady salient region detector which result in a significant improvement in performance. The modifications we make include: stabilising the difference between consecutive scales when calculating the inter-scale saliency, a new sampling strategy using overlap of pixels, partial volume estimation and parzen windowing. Repeatability is used as the criterion for evaluating the performance of the algorithm. We observe the repeatability for distinctive regions selected from an image and from the same image after applying a particular transformation. The transformations we use include planar rotation, pixel translation, spatial scaling, and intensity shifts and scaling. Experimental results show that the average repeatability rate is improved from 46% to approximately 78% when all the enhancements are applied. We also compare our algorithm with other region detectors on a set of sequences of real images, and our detector outperforms most of the state of the art detectors.

Item Type: Article
Uncontrolled Keywords: Visual saliency; Feature detection; Repeatability; Entropy; Scale selection; Partial volume estimation; Parzen window; Bin interpolation
Subjects: G400 Computer Science
Department: Faculties > Engineering and Environment > Computer and Information Sciences
Depositing User: Paul Burns
Date Deposited: 15 Jun 2015 13:10
Last Modified: 03 Nov 2016 11:36
URI: http://nrl.northumbria.ac.uk/id/eprint/22905

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics


Policies: NRL Policies | NRL University Deposit Policy | NRL Deposit Licence