Using the thresholds function method to detect license plates

Seiki Yoshimori, Yasue Mitsukura, Minoru Fukumi, Norio Akamatsu

Research output: Contribution to journalArticle

Abstract

License plate recognition is very important technology for regulating an automobile society, However, doing so it is very difficult, because a background and a car surface color can be similar to that of the license plate. Furthermore, detecting license plates when cars are moving at a very high speed is difficult. In this paper, We propose a new method of extracting car license plates automatically by using a real-coded genetic algorithm(RGA). Using the proposed RGA, the most likely plate colors can be detected under various light conditions. First, the average brightness Y value of images are calculated. Next, the retation between the Y value and the most likely plate color thresholds upper and lower bounds are obtained with the RGA to estimate threshold equations. To prove the effectiveness of the proposed method, we describe simulations performed using real images.

Original languageEnglish
Pages (from-to)115-122
Number of pages8
JournalKyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers
Volume59
Issue number1
Publication statusPublished - 2005 Jan
Externally publishedYes

Fingerprint

Railroad cars
Genetic algorithms
Automobiles
Luminance
Color

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Computer Vision and Pattern Recognition

Cite this

Using the thresholds function method to detect license plates. / Yoshimori, Seiki; Mitsukura, Yasue; Fukumi, Minoru; Akamatsu, Norio.

In: Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, Vol. 59, No. 1, 01.2005, p. 115-122.

Research output: Contribution to journalArticle

@article{fbf776ab0ea74a2690dd4f6d1d89ebe5,
title = "Using the thresholds function method to detect license plates",
abstract = "License plate recognition is very important technology for regulating an automobile society, However, doing so it is very difficult, because a background and a car surface color can be similar to that of the license plate. Furthermore, detecting license plates when cars are moving at a very high speed is difficult. In this paper, We propose a new method of extracting car license plates automatically by using a real-coded genetic algorithm(RGA). Using the proposed RGA, the most likely plate colors can be detected under various light conditions. First, the average brightness Y value of images are calculated. Next, the retation between the Y value and the most likely plate color thresholds upper and lower bounds are obtained with the RGA to estimate threshold equations. To prove the effectiveness of the proposed method, we describe simulations performed using real images.",
author = "Seiki Yoshimori and Yasue Mitsukura and Minoru Fukumi and Norio Akamatsu",
year = "2005",
month = "1",
language = "English",
volume = "59",
pages = "115--122",
journal = "Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers",
issn = "1342-6907",
publisher = "Institute of Image Information and Television Engineers",
number = "1",

}

TY - JOUR

T1 - Using the thresholds function method to detect license plates

AU - Yoshimori, Seiki

AU - Mitsukura, Yasue

AU - Fukumi, Minoru

AU - Akamatsu, Norio

PY - 2005/1

Y1 - 2005/1

N2 - License plate recognition is very important technology for regulating an automobile society, However, doing so it is very difficult, because a background and a car surface color can be similar to that of the license plate. Furthermore, detecting license plates when cars are moving at a very high speed is difficult. In this paper, We propose a new method of extracting car license plates automatically by using a real-coded genetic algorithm(RGA). Using the proposed RGA, the most likely plate colors can be detected under various light conditions. First, the average brightness Y value of images are calculated. Next, the retation between the Y value and the most likely plate color thresholds upper and lower bounds are obtained with the RGA to estimate threshold equations. To prove the effectiveness of the proposed method, we describe simulations performed using real images.

AB - License plate recognition is very important technology for regulating an automobile society, However, doing so it is very difficult, because a background and a car surface color can be similar to that of the license plate. Furthermore, detecting license plates when cars are moving at a very high speed is difficult. In this paper, We propose a new method of extracting car license plates automatically by using a real-coded genetic algorithm(RGA). Using the proposed RGA, the most likely plate colors can be detected under various light conditions. First, the average brightness Y value of images are calculated. Next, the retation between the Y value and the most likely plate color thresholds upper and lower bounds are obtained with the RGA to estimate threshold equations. To prove the effectiveness of the proposed method, we describe simulations performed using real images.

UR - http://www.scopus.com/inward/record.url?scp=15744389435&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=15744389435&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:15744389435

VL - 59

SP - 115

EP - 122

JO - Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers

JF - Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers

SN - 1342-6907

IS - 1

ER -