Real-time search-free multiple license plate recognition via likelihood estimation of saliency

Safaei, A ORCID: https://orcid.org/0000-0003-4696-8968, Tang, HL and Sanei, S ORCID: https://orcid.org/0000-0002-3437-2801, 2016. Real-time search-free multiple license plate recognition via likelihood estimation of saliency. Computers and Electrical Engineering: an International Journal, 56, pp. 15-29. ISSN 0045-7906

Preview

Text PubSub10183_Sanei.pdf - Post-print Download (3MB) | Preview

Abstract

In this paper, we propose a novel search-free localization method based on 3-D Bayesian saliency estimation. This method uses a new 3-D object tracking algorithm which includes: object detection, shadow detection and removal, and object recognition based on Bayesian methods. The algorithm is tested over three image datasets with different levels of complexities, and the results are compared with those of benchmark methods in terms of speed and accuracy. Unlike most search-based license-plate extraction methods, our proposed 3-D Bayesian saliency algorithm has lower execution time (less than 60 ms), more accuracy, and it is a search-free algorithm which works in noisy backgrounds.

Item Type:	Journal article
Publication Title:	Computers and Electrical Engineering: an International Journal
Creators:	Safaei, A., Tang, H.L. and Sanei, S.
Publisher:	Elsevier Ltd.
Date:	November 2016
Volume:	56
ISSN:	0045-7906
Identifiers:	Number Type 10.1016/j.compeleceng.2016.09.010 DOI S0045790616302531 Publisher Item Identifier
Divisions:	Schools > School of Science and Technology
Record created by:	Jill Tomkinson
Date Added:	13 Feb 2018 14:26
Last Modified:	31 Aug 2018 14:11
URI:	https://irep.ntu.ac.uk/id/eprint/32693

Actions (login required)

Edit View

Statistics

Views

Downloads