Two-Stage License Plate Detection Using Gentle Adaboost and SIFT-SVM

Author

Ho, Wing Teng ; Lim, Hao Wooi ; Tay, Yong Haur

Author_Institution

Comput. Vision & Intell. Syst. (CVIS) group, Univ. Tunku Abdul Rahman (UTAR), Petaling Jaya, Malaysia

fYear

2009

fDate

1-3 April 2009

Firstpage

109

Lastpage

114

Abstract

This paper presents a two-stage method to detect license plates in real world images. To do license plate detection (LPD), an initial set of possible license plate character regions are first obtained by the first stage classifier and then passed to the second stage classifier to reject non-character regions. 36 Adaboost classifiers (each trained with one alpha-numerical character, i.e. A..Z, 0..9) serve as the first stage classifier. In the second stage, a support vector machine (SVM) trained on scale-invariant feature transform (SIFT) descriptors obtained from training sub-windows were employed. A recall rate of 0.920792 and precision rate of 0.90185 was obtained.

Keywords

character recognition; image classification; support vector machines; traffic engineering computing; Adaboost classifiers; first stage classifier; gentle Adaboost; license plate character regions; noncharacter regions; real world images; scale-invariant feature transform descriptors; second stage classifier; support vector machine; two-stage license plate detection; Database systems; Deductive databases; Face detection; Licenses; Robustness; Support vector machine classification; Support vector machines; Vehicle detection; Vehicle driving; Vehicles; Adaboost; License plate detection; SIFT; SVM;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Information and Database Systems, 2009. ACIIDS 2009. First Asian Conference on

Conference_Location

Dong Hoi

Print_ISBN

978-0-7695-3580-7

Type

conf

DOI

10.1109/ACIIDS.2009.25

Filename

5175977