期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2012
卷号：45
期号：1
页码：027-032
出版社：Journal of Theoretical and Applied
摘要：License plates localization is an important task for the recognition of Vehicle License Plates (VLP). To deal with this issue, a number of approaches have been proposed. These include texture-based, morphology-based and boundary line-based approaches. In this paper, we present a new texture-based algorithm to detect and localize license plates in images. Yet, focus will be laid on Moroccan VLP. Analysis has actually revealed that the proposed algorithm achieves high accuracy in plate localization. For evaluation purposes, various images taken from different distances and in different angles were used. The experimental results show that our system can efficiently detect and localize the VLP in images. Indeed, the recall/precision curve of the proposed method proves that 84.21% precision rate is obtained for recall rate value equals 80%, while the value of the standard measure of quality is equal to 82.05%.
