Libyan vehicle plate recognition using regionbased features and probabilistic neural network

Khadija Ahmad Jabar, Mohammad Faidzul Nasrudin

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Automatic License Plate Recognition (ALPR) has wide range of commercial applications such as finding stolen cars, controlling access to car parks and gathering traffic flow statistics. Existing Libyan License Plate Recognition (LLPR) methods are not presented promising results due to their inefficient features for the extracted characters and numbers. In this work, an improved LLPR method is presented. The method is composed of five stages: pre-processing, license plate extraction, character and numbers segmentation, feature extraction and license plate recognition. In the pre-processing, undesired data, such as background noises are removed. Then, the license plate is extracted using few mathematical morphologies, Connected Component Analysis (CCA) and Region of Interest (ROI) extraction. After that, characters and numbers from the image regions of the license plate are extracted. A combination of geometrical features and Gabor features are considered to represent each of the character and word in the plates. Then, the recognition is done by using a template matching and a Probabilistic Neural Network (PNN) classification. The performance of the proposed method is evaluated and tested using 100 self-collected images of Libyan national license plates. The experimental results have shown that the proposed method has produced promising results and superior than other existing methods.

Original languageEnglish
Pages (from-to)104-114
Number of pages11
JournalJournal of Theoretical and Applied Information Technology
Volume94
Issue number1
Publication statusPublished - 15 Dec 2016

Fingerprint

Probabilistic Neural Network
Railroad cars
Neural networks
Mathematical morphology
Template matching
Feature extraction
Statistics
Processing
Data Preprocessing
Mathematical Morphology
Template Matching
Region of Interest
Traffic Flow
Connected Components
Feature Extraction
Preprocessing
Segmentation

Keywords

  • Automatic license plate recognition
  • Feature extraction
  • Image processing
  • Probabilistic Neural network

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Cite this

Libyan vehicle plate recognition using regionbased features and probabilistic neural network. / Jabar, Khadija Ahmad; Nasrudin, Mohammad Faidzul.

In: Journal of Theoretical and Applied Information Technology, Vol. 94, No. 1, 15.12.2016, p. 104-114.

Research output: Contribution to journalArticle

@article{b1b855b35c2348129151dfdb97abd718,
title = "Libyan vehicle plate recognition using regionbased features and probabilistic neural network",
abstract = "Automatic License Plate Recognition (ALPR) has wide range of commercial applications such as finding stolen cars, controlling access to car parks and gathering traffic flow statistics. Existing Libyan License Plate Recognition (LLPR) methods are not presented promising results due to their inefficient features for the extracted characters and numbers. In this work, an improved LLPR method is presented. The method is composed of five stages: pre-processing, license plate extraction, character and numbers segmentation, feature extraction and license plate recognition. In the pre-processing, undesired data, such as background noises are removed. Then, the license plate is extracted using few mathematical morphologies, Connected Component Analysis (CCA) and Region of Interest (ROI) extraction. After that, characters and numbers from the image regions of the license plate are extracted. A combination of geometrical features and Gabor features are considered to represent each of the character and word in the plates. Then, the recognition is done by using a template matching and a Probabilistic Neural Network (PNN) classification. The performance of the proposed method is evaluated and tested using 100 self-collected images of Libyan national license plates. The experimental results have shown that the proposed method has produced promising results and superior than other existing methods.",
keywords = "Automatic license plate recognition, Feature extraction, Image processing, Probabilistic Neural network",
author = "Jabar, {Khadija Ahmad} and Nasrudin, {Mohammad Faidzul}",
year = "2016",
month = "12",
day = "15",
language = "English",
volume = "94",
pages = "104--114",
journal = "Journal of Theoretical and Applied Information Technology",
issn = "1992-8645",
publisher = "Asian Research Publishing Network (ARPN)",
number = "1",

}

TY - JOUR

T1 - Libyan vehicle plate recognition using regionbased features and probabilistic neural network

AU - Jabar, Khadija Ahmad

AU - Nasrudin, Mohammad Faidzul

PY - 2016/12/15

Y1 - 2016/12/15

N2 - Automatic License Plate Recognition (ALPR) has wide range of commercial applications such as finding stolen cars, controlling access to car parks and gathering traffic flow statistics. Existing Libyan License Plate Recognition (LLPR) methods are not presented promising results due to their inefficient features for the extracted characters and numbers. In this work, an improved LLPR method is presented. The method is composed of five stages: pre-processing, license plate extraction, character and numbers segmentation, feature extraction and license plate recognition. In the pre-processing, undesired data, such as background noises are removed. Then, the license plate is extracted using few mathematical morphologies, Connected Component Analysis (CCA) and Region of Interest (ROI) extraction. After that, characters and numbers from the image regions of the license plate are extracted. A combination of geometrical features and Gabor features are considered to represent each of the character and word in the plates. Then, the recognition is done by using a template matching and a Probabilistic Neural Network (PNN) classification. The performance of the proposed method is evaluated and tested using 100 self-collected images of Libyan national license plates. The experimental results have shown that the proposed method has produced promising results and superior than other existing methods.

AB - Automatic License Plate Recognition (ALPR) has wide range of commercial applications such as finding stolen cars, controlling access to car parks and gathering traffic flow statistics. Existing Libyan License Plate Recognition (LLPR) methods are not presented promising results due to their inefficient features for the extracted characters and numbers. In this work, an improved LLPR method is presented. The method is composed of five stages: pre-processing, license plate extraction, character and numbers segmentation, feature extraction and license plate recognition. In the pre-processing, undesired data, such as background noises are removed. Then, the license plate is extracted using few mathematical morphologies, Connected Component Analysis (CCA) and Region of Interest (ROI) extraction. After that, characters and numbers from the image regions of the license plate are extracted. A combination of geometrical features and Gabor features are considered to represent each of the character and word in the plates. Then, the recognition is done by using a template matching and a Probabilistic Neural Network (PNN) classification. The performance of the proposed method is evaluated and tested using 100 self-collected images of Libyan national license plates. The experimental results have shown that the proposed method has produced promising results and superior than other existing methods.

KW - Automatic license plate recognition

KW - Feature extraction

KW - Image processing

KW - Probabilistic Neural network

UR - http://www.scopus.com/inward/record.url?scp=85006506876&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85006506876&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85006506876

VL - 94

SP - 104

EP - 114

JO - Journal of Theoretical and Applied Information Technology

JF - Journal of Theoretical and Applied Information Technology

SN - 1992-8645

IS - 1

ER -