University of Khartoum

Sudanese License Plate Recognition System

Sudanese License Plate Recognition System

Show full item record

Title: Sudanese License Plate Recognition System
Author: Basheer, Hazim Naiem Abdulaal
Abstract: In the modern era, computers are used to automate most of the operations used to be done by humans. This leads to higher performance and low cost of operations. The field of traffic management is not an exception. License plate is an identifier that uniquely differentiate each vehicle from others. Automated traffic management requires a computer to be able to identify each vehicle using its license plate. This is accomplished using license plate recognition systems. In this work, Sudanese license plate recognition system is developed. The system is capable of identifying Sudanese private cars using their license plates. The system is operating using three steps, locating the license plate in the image, segmenting the numbers in the plate and recognize each number individually to obtain the result. Locating the license plate is done using template matching method with the help of edge detection using Canny’s method and contours extraction, which are used to minimize the time of the operation and solving the skewed images. Numbers on the plate are segmented for higher accuracy in recognition, it’s accomplished using connected components algorithm to extract each number individually. Finally, each extracted number is recognized using Support Vector Machine classifier after obtaining a descriptor of each image. Histogram of Oriented Gradient is used as a descriptor of images. The system performed well for these three steps. Obtaining an overall accuracy of about 87%. The system performance is also acceptable, but not high enough to be used in real-time applications
URI: http://khartoumspace.uofk.edu/123456789/25811
Date: 2017


Files in this item

Files Size Format View

This item appears in the following Collection(s)

Show full item record

Share

Search DSpace


Browse

My Account