Date of Award

2016

Publication Type

Master Thesis

Degree Name

M.Sc.

Department

Computer Science

First Advisor

Imran Ahmad

Keywords

Character recognition, Character segmentation, Licence Plate Detection, Number plate localization, Template Matching, Vehicle Shape Detection

Rights

info:eu-repo/semantics/openAccess

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Abstract

Security is extremely concerning point in distinctive applications, and in vehicle identification it is obligatory to raise alert on any suspicious activity. Such models can be utilized as a part of Border Security, Bank Security etc. In order to detect any vehicle we need to extract its features. Machine vision can be used to extract these features. Furthermore, vehicles have some of the features that may not be unique e.g. color, shape etc. Nevertheless, license plate is a unique identity of a vehicle which can identify its owner. Conversely, it can be tampered with and can be transferred to different vehicle easily. Hence we propose a new model which will combine automated license plate detection along with shape of the vehicle for e.g. SUV, Sedan and Hatchback. Finally, we compare our results with the database which has the legitimate features and information of that vehicle and which will automatically, raise an alert if any discrepancy is found.

Share

COinS