Vehicle licence plate recognition by grey-scale morphology

Pao Yue-kong Library Electronic Theses Database

Vehicle licence plate recognition by grey-scale morphology

 

Author: Lau, Man-sheung
Title: Vehicle licence plate recognition by grey-scale morphology
Degree: M.Sc.
Year: 1994
Subject: Automobile license plates -- Identification
Morphisms (Mathematics)
Image processing -- Mathematics
Hong Kong Polytechnic -- Dissertations
Department: Dept. of Electronic Engineering
Pages: 75, [26] leaves : ill. ; 31 cm
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b1158276
URI: http://theses.lib.polyu.edu.hk/handle/200/4609
Abstract: In recent years, mathematical morphology becomes an important area in image processing. Its applications are various. For example, to recognise grey-scale natural scene image, grey-scale morphology can be used. This project proposes five algorithms which use grey-scale morphology to detect the features of the characters on the vehicle licence plates in natural scene images and two postprocessings to properly extract the region of the licence plates. The algorithms are tested and compared. Their results are also presented at the end of this report. Natural scene images containing the licence plates are taken from a camera, and no special constraint is imposed on the images except that the licence plates should not be inclined significantly. Algorithm I detects inner side of corners. Algorithm II detects character spacings and horizontal lines. Algorithm III is similar to Algorithm II but the speed is increased. Algorithm IV detects partially enclosed areas. Algorithm V is similar to Algorithm IV but the speed is increased. Stage I Postprocessing is to eliminate the dark outer regions. Stage II Postprocessing is to seek the truncated parts of the licence plates and remove the over detected areas. A development platform is developed for implementing and testing the algorithms and postprocessings. The development platform allows user to execute instructions step by step or in batch. Experiment results show that the algorithms and postprocessings are feasible, and successful rate is high especially for Algorithm II with Stage I and II Postprocessing. The system in this project can be combined with a common character recognition program to form an automatic licence number recognition system. It can be placed at roadside, tunnel entrance or car park to automatically record the licence number of the vehicle passing by for security, traffic monitoring or recording purposes.

Files in this item

Files Size Format
b11582765.pdf 8.739Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

     

Quick Search

Browse

More Information