Mean shift for accurate license plate localization

Publication Type:
Conference Proceeding
IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, 2005, 2005 pp. 566 - 571
Issue Date:
Full metadata record
This paper presents a region-based algorithm for accurate license plate localization, where mean shift is utilized to filter and segment color vehicle images into candidate regions. Three features are extracted in order to decide whether a candidate region represents a real license plate, namely, rectangularity, aspect ratio, and edge density. Then, the Mahalanobis classifier is used with respect to above three features to classify license plate regions and non-license plate regions. Experimental results show that the proposed algorithm produces high robustness and accuracy. © 2005 IEEE.
Please use this identifier to cite or link to this item: