Research Repository

Assessing the performance bounds of local feature detectors: Taking inspiration from electronics design practices

Ehsan, Shoaib and Clark, Adrian F and Ferrarini, Bruno and Rehman, Naveed Ur and McDonald-Maier, Klaus D (2015) Assessing the performance bounds of local feature detectors: Taking inspiration from electronics design practices. In: 2015 International Conference on Systems, Signals and Image Processing (IWSSIP), 2015-09-10 - 2015-09-12, London.

[img]
Preview
Text
1510.05156.pdf - Accepted Version

Download (869kB) | Preview

Abstract

Since local feature detection has been one of the most active research areas in computer vision, a large number of detectors have been proposed. This has rendered the task of characterizing the performance of various feature detection methods an important issue in vision research. Inspired by the good practices of electronic system design, a generic framework based on the improved repeatability measure is presented in this paper that allows assessment of the upper and lower bounds of detector performance in an effort to design more reliable and effective vision systems. This framework is then employed to establish operating and guarantee regions for several state-of-the art detectors for JPEG compression and uniform light changes. The results are obtained using a newly acquired, large image database (15092 images) with 539 different scenes. These results provide new insights into the behavior of detectors and are also useful from the vision systems design perspective.

Item Type: Conference or Workshop Item (Paper)
Additional Information: Published proceedings: 2015 International Conference on Systems, Signals and Image Processing (IWSSIP)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Jim Jamieson
Date Deposited: 01 Jul 2016 15:42
Last Modified: 22 Jul 2020 08:15
URI: http://repository.essex.ac.uk/id/eprint/17127

Actions (login required)

View Item View Item