1. UKM Learning and Research Repository
2. Master Thesis / Tesis Master
3. Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat

Title:	Libyan vehicle plate recognition using region-based features and probabilistic neural network
Authors:	Khdija A H Jabar (P65627)
Supervisor:	Mohammad Faidzul Nasrudin, Dr.
Keywords:	Neural networks (Computer science) Vehicle detectors Support vector machines Universiti Kebangsaan Malaysia -- Dissertations Dissertations, Academic -- Malaysia
Issue Date:	8-Sep-2016
Description:	Automatic License Plate Recognition (ALPR) is a challenging issue of computer vision research area due to its importance to a wide range of commercial applications such as finding stolen cars, controlling access to car parks and gathering traffic flow statistics. The ALPR generally aims to detect the license plate and recognize its characters. The ALPR is principally consisted of stages as pre-processing, license plate extraction, character segmentation, feature extraction and recognition. In ALPR, variety of plate structures including colors, backgrounds, foregrounds, fonts and styles from one country to another, make the ALPR is a challenging issue in which open the problem to be researched on this area. This research concentrates on Libyan License Plate Recognition. Although various detection and recognition methods that have been proposed in the previous studies, a few studies had investigated on the Libyan plate. Besides that, the existing Libyan plate recognition methods do not present promising results due to inefficient features extraction for characters and numbers recognition. Therefore, it is required to explore other feature extraction methods to describe the plate contents effectively to improve the recognition performance. Thus, this thesis presents an integrated approach for detecting and recognizing Libyan license plates based on region-based features and Probabilistic Neural Network (PNN). The method begins with the pre-processing of the image using thresholding and morphological operations. In the plate extraction stage, connected component analysis is utilized to locate unique objects, from which the unwanted objects are removed using the filtering process. Global region-based features are used to prepare the identified objects before their classification as Plate and nonPlate using PNN. In the recognition process, for character segmentation, a simple template is derived to extract and differentiate digits and Arabic words, as the Arabic word is not segmented into individual letters like the digits. The outputs are improved using the median filtering and connected component analysis. The performance of the proposed method is evaluated and tested using 100 self-collected images of Libyan national license plates. Experimental results have shown that the proposed method has produced promising results. Furthermore, a quantitative comparison has conducted to demonstrate the proposed method produces a better recognition rate compared to the other existing methods.,Master of Information Technology,Certification of Master's / Doctoral Thesis" is not available"
Pages:	87
Call Number:	QA76.87.J333 2016 3 tesis
Publisher:	UKM, Bangi
Appears in Collections:	Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.