No Detail Found!

A novel texture-based algorithm for localizing vehicle license plates.

Author(s)
Hinde Anoual Lrit, Unité Associée Au Cnrst, Urac 29, Fsr, Université Mohammed V Agdal, Rabat
Driss Aboutajdine Lrit, Unité Associée Au Cnrst, Urac 29, Fsr, Université Mohammed V Agdal, Rabat
Sanaa El-Fkihi Ensias, Université Mohammed V Souissi, Rabat
Abdeilah Jilbab Enset, Université Mohammed V Souissi, Rabat
Abstract
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%.
Publication Details
Page(s) 27-32
DOI DOI not available
Published Journal: Journal of Theoretical and Applied Information Technology, Volume: 45, Issue: 1, Year: 2012

Request the full text from PASTIC

More from Journal of Theoretical and Applied Information Technology
0

Citations

0

Downloads

152

Views

Copyright ©  PASTIC National Center, Islamabad www.pastic.gov.pk