vehicle Identification by license plate using support vector machine (SVM)

No Thumbnail Available

Date

2016

Journal Title

Journal ISSN

Volume Title

Publisher

UNIVERSITE DE M’SILA : FACULTE DES MATHEMATIQUES ET DE L’INFORMATIQUE : Département d’Informatique

Abstract

The Automatic Number plate recognition it is a mass surveillance method that uses optical character recognition on images to read vehicle registration plates, it is playing an important role in variety of applications related to automated transport system such as road traffic monitoring, detection of stolen vehicles, automatic payments of tolls on highways or bridges, parking lots access control etc. It has to be quickly and successfully process license plates (LP) under different environmental conditions, such as indoors, outdoors, day or night time. In this work we are showing different techniques used for ANPR, used two methods : Hu variants moment and local binary pattern (LBP) for feature extraction , and two methods for classification support vector machine (SVM) and template matching (KNN). In Experimental results, we have obtained the best recognition rate of 80% using Hu variants moment and SVM.

Description

Keywords

ANPR, support vector machine (SVM), Hu variants moment, LP, local binary pattern (LBP), edge detection.

Citation

Collections