Bruce, B.R., Aitken, J.M. orcid.org/0000-0003-4204-4020 and Petke, J. (2016) Deep parameter optimisation for face detection using the Viola-Jones algorithm in OpenCV. In: Sarro, F and Deb, K, (eds.) Search Based Software Engineering. SSBSE 2016. SSBSE 2016: International Symposium on Search Based Software Engineering, 08-10 Oct 2016, Raleigh, NC, USA. Lecture Notes in Computer Science (9962). Springer International Publishing , pp. 238-243. ISBN 9783319471051
Abstract
OpenCV is a commonly used computer vision library containing a wide variety of algorithms for the AI community. This paper uses deep parameter optimisation to investigate improvements to face detection using the Viola-Jones algorithm in OpenCV, allowing a trade-off between execution time and classification accuracy. Our results show that execution time can be decreased by 48 % if a 1.80 % classification inaccuracy is permitted (compared to 1.04 % classification inaccuracy of the original, unmodified algorithm). Further execution time savings are possible depending on the degree of inaccuracy deemed acceptable by the user.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Editors: |
|
Copyright, Publisher and Additional Information: | © Springer International Publishing AG 2016. This is an author-produced version of a paper subsequently published in SSBSE 2016 proceedings. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | Deep parameter optimisation; Automated parameter tuning; Multi-objective optimisation; Genetic improvement; GI; SBSE; OpenCV; Viola-Jones Algorithm |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Automatic Control and Systems Engineering (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 15 Jul 2019 11:26 |
Last Modified: | 16 Jul 2019 10:53 |
Status: | Published |
Publisher: | Springer International Publishing |
Series Name: | Lecture Notes in Computer Science |
Refereed: | Yes |
Identification Number: | 10.1007/978-3-319-47106-8_18 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:146927 |