License plate detection and segmentation using cluster run length smoothing algorithm

Siti Norul Huda Sheikh Abdullah, Muhammad Nuruddin Sudin, Anton Satria Prabuwono, Teddy Mantoro

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

For the different types of license plates being used, the requirement of an automatic license plate recognition system is different for each country. In this paper, an automatic license plate detection system is proposed for Malaysian vehicles with standard license plates based on image processing and clustering. Detecting the location of license plate is a vital issue when dealing with uncontrolled environments and illumination diffi-culty. Therefore, a proposed algorithm called Cluster Run Length Smoothing Algorithm (CRLSA) was applied to locate the license plates at the right position. CRLSA consisted of two separate proposed algorithms which applied run length edge detector algorithm using 3 × 3 kernel masks and 128 grayscale offset plus a three-dimensional way to calculate run length smoothing algorithm, which can improve clustering techniques in segmentation phase. Six separate experiments were performed; Morphology, CRLSA, Clustering, Square/Contour Detection, Hough, and Radon Transform. From those experiments, analysis based on segmentation errors was constructed. The prototyped system has accuracy more than 96%.

Original languageEnglish
Pages (from-to)46-70
Number of pages25
JournalJournal of Information Technology Research
Volume5
Issue number3
DOIs
Publication statusPublished - Jul 2012

Fingerprint

Radon
Clustering algorithms
Masks
Image processing
Lighting
Experiments
Mathematical transformations
Detectors

Keywords

  • Clustering
  • Image Detection
  • License Plate Recognition
  • Run Length Smoothing Algorithm

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

License plate detection and segmentation using cluster run length smoothing algorithm. / Sheikh Abdullah, Siti Norul Huda; Sudin, Muhammad Nuruddin; Prabuwono, Anton Satria; Mantoro, Teddy.

In: Journal of Information Technology Research, Vol. 5, No. 3, 07.2012, p. 46-70.

Research output: Contribution to journalArticle

Sheikh Abdullah, Siti Norul Huda ; Sudin, Muhammad Nuruddin ; Prabuwono, Anton Satria ; Mantoro, Teddy. / License plate detection and segmentation using cluster run length smoothing algorithm. In: Journal of Information Technology Research. 2012 ; Vol. 5, No. 3. pp. 46-70.
@article{86e00cc0a02f40518323aa405a5f5875,
title = "License plate detection and segmentation using cluster run length smoothing algorithm",
abstract = "For the different types of license plates being used, the requirement of an automatic license plate recognition system is different for each country. In this paper, an automatic license plate detection system is proposed for Malaysian vehicles with standard license plates based on image processing and clustering. Detecting the location of license plate is a vital issue when dealing with uncontrolled environments and illumination diffi-culty. Therefore, a proposed algorithm called Cluster Run Length Smoothing Algorithm (CRLSA) was applied to locate the license plates at the right position. CRLSA consisted of two separate proposed algorithms which applied run length edge detector algorithm using 3 × 3 kernel masks and 128 grayscale offset plus a three-dimensional way to calculate run length smoothing algorithm, which can improve clustering techniques in segmentation phase. Six separate experiments were performed; Morphology, CRLSA, Clustering, Square/Contour Detection, Hough, and Radon Transform. From those experiments, analysis based on segmentation errors was constructed. The prototyped system has accuracy more than 96{\%}.",
keywords = "Clustering, Image Detection, License Plate Recognition, Run Length Smoothing Algorithm",
author = "{Sheikh Abdullah}, {Siti Norul Huda} and Sudin, {Muhammad Nuruddin} and Prabuwono, {Anton Satria} and Teddy Mantoro",
year = "2012",
month = "7",
doi = "10.4018/jitr.2012070103",
language = "English",
volume = "5",
pages = "46--70",
journal = "Journal of Information Technology Research",
issn = "1938-7857",
publisher = "The Information Resources Management Association (IRMA)",
number = "3",

}

TY - JOUR

T1 - License plate detection and segmentation using cluster run length smoothing algorithm

AU - Sheikh Abdullah, Siti Norul Huda

AU - Sudin, Muhammad Nuruddin

AU - Prabuwono, Anton Satria

AU - Mantoro, Teddy

PY - 2012/7

Y1 - 2012/7

N2 - For the different types of license plates being used, the requirement of an automatic license plate recognition system is different for each country. In this paper, an automatic license plate detection system is proposed for Malaysian vehicles with standard license plates based on image processing and clustering. Detecting the location of license plate is a vital issue when dealing with uncontrolled environments and illumination diffi-culty. Therefore, a proposed algorithm called Cluster Run Length Smoothing Algorithm (CRLSA) was applied to locate the license plates at the right position. CRLSA consisted of two separate proposed algorithms which applied run length edge detector algorithm using 3 × 3 kernel masks and 128 grayscale offset plus a three-dimensional way to calculate run length smoothing algorithm, which can improve clustering techniques in segmentation phase. Six separate experiments were performed; Morphology, CRLSA, Clustering, Square/Contour Detection, Hough, and Radon Transform. From those experiments, analysis based on segmentation errors was constructed. The prototyped system has accuracy more than 96%.

AB - For the different types of license plates being used, the requirement of an automatic license plate recognition system is different for each country. In this paper, an automatic license plate detection system is proposed for Malaysian vehicles with standard license plates based on image processing and clustering. Detecting the location of license plate is a vital issue when dealing with uncontrolled environments and illumination diffi-culty. Therefore, a proposed algorithm called Cluster Run Length Smoothing Algorithm (CRLSA) was applied to locate the license plates at the right position. CRLSA consisted of two separate proposed algorithms which applied run length edge detector algorithm using 3 × 3 kernel masks and 128 grayscale offset plus a three-dimensional way to calculate run length smoothing algorithm, which can improve clustering techniques in segmentation phase. Six separate experiments were performed; Morphology, CRLSA, Clustering, Square/Contour Detection, Hough, and Radon Transform. From those experiments, analysis based on segmentation errors was constructed. The prototyped system has accuracy more than 96%.

KW - Clustering

KW - Image Detection

KW - License Plate Recognition

KW - Run Length Smoothing Algorithm

UR - http://www.scopus.com/inward/record.url?scp=84870352317&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870352317&partnerID=8YFLogxK

U2 - 10.4018/jitr.2012070103

DO - 10.4018/jitr.2012070103

M3 - Article

VL - 5

SP - 46

EP - 70

JO - Journal of Information Technology Research

JF - Journal of Information Technology Research

SN - 1938-7857

IS - 3

ER -