A Design of the Object Detection System Using the RGA

Seiki Yoshimori, Yasue Mitsukura, Minora Fukumi, Norio Akamatsu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

License plate recognition is very important in an automobile society. However, it is very difficult to do it, because a background and a body color of cars are similar to that of the license plate. Furthermore, the detection of cars in a moving at a very high-speed is difficult to be done. In this paper, we propose a new robust thresholds determination method in the various background by using the real coded genetic algorithm (RGA). By using RGA, the most likely plate colors are decided under various light conditions. First, the average brightness Y values of images are calculated. Next, relationship between the Y value and the most likely plate color thresholds (upper and lower bounds) are obtained by GA to estimate threshold equations by using the recursive least squares (RLS) algorithm. Finally, in order to show the effectiveness of the proposed method, we show simulation examples by using real images, and result rate of detection is 85.0%.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages1227-1231
Number of pages5
Volume2
Publication statusPublished - 2003
Externally publishedYes
EventInternational Joint Conference on Neural Networks 2003 - Portland, OR, United States
Duration: 2003 Jul 202003 Jul 24

Other

OtherInternational Joint Conference on Neural Networks 2003
CountryUnited States
CityPortland, OR
Period03/7/2003/7/24

Fingerprint

Railroad cars
Genetic algorithms
License plates (automobile)
Automobiles
Luminance
Color
Object detection

ASJC Scopus subject areas

  • Software

Cite this

Yoshimori, S., Mitsukura, Y., Fukumi, M., & Akamatsu, N. (2003). A Design of the Object Detection System Using the RGA. In Proceedings of the International Joint Conference on Neural Networks (Vol. 2, pp. 1227-1231)

A Design of the Object Detection System Using the RGA. / Yoshimori, Seiki; Mitsukura, Yasue; Fukumi, Minora; Akamatsu, Norio.

Proceedings of the International Joint Conference on Neural Networks. Vol. 2 2003. p. 1227-1231.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yoshimori, S, Mitsukura, Y, Fukumi, M & Akamatsu, N 2003, A Design of the Object Detection System Using the RGA. in Proceedings of the International Joint Conference on Neural Networks. vol. 2, pp. 1227-1231, International Joint Conference on Neural Networks 2003, Portland, OR, United States, 03/7/20.
Yoshimori S, Mitsukura Y, Fukumi M, Akamatsu N. A Design of the Object Detection System Using the RGA. In Proceedings of the International Joint Conference on Neural Networks. Vol. 2. 2003. p. 1227-1231
Yoshimori, Seiki ; Mitsukura, Yasue ; Fukumi, Minora ; Akamatsu, Norio. / A Design of the Object Detection System Using the RGA. Proceedings of the International Joint Conference on Neural Networks. Vol. 2 2003. pp. 1227-1231
@inproceedings{8b3b76ef75284efa857c18801e1fee9e,
title = "A Design of the Object Detection System Using the RGA",
abstract = "License plate recognition is very important in an automobile society. However, it is very difficult to do it, because a background and a body color of cars are similar to that of the license plate. Furthermore, the detection of cars in a moving at a very high-speed is difficult to be done. In this paper, we propose a new robust thresholds determination method in the various background by using the real coded genetic algorithm (RGA). By using RGA, the most likely plate colors are decided under various light conditions. First, the average brightness Y values of images are calculated. Next, relationship between the Y value and the most likely plate color thresholds (upper and lower bounds) are obtained by GA to estimate threshold equations by using the recursive least squares (RLS) algorithm. Finally, in order to show the effectiveness of the proposed method, we show simulation examples by using real images, and result rate of detection is 85.0{\%}.",
author = "Seiki Yoshimori and Yasue Mitsukura and Minora Fukumi and Norio Akamatsu",
year = "2003",
language = "English",
volume = "2",
pages = "1227--1231",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - A Design of the Object Detection System Using the RGA

AU - Yoshimori, Seiki

AU - Mitsukura, Yasue

AU - Fukumi, Minora

AU - Akamatsu, Norio

PY - 2003

Y1 - 2003

N2 - License plate recognition is very important in an automobile society. However, it is very difficult to do it, because a background and a body color of cars are similar to that of the license plate. Furthermore, the detection of cars in a moving at a very high-speed is difficult to be done. In this paper, we propose a new robust thresholds determination method in the various background by using the real coded genetic algorithm (RGA). By using RGA, the most likely plate colors are decided under various light conditions. First, the average brightness Y values of images are calculated. Next, relationship between the Y value and the most likely plate color thresholds (upper and lower bounds) are obtained by GA to estimate threshold equations by using the recursive least squares (RLS) algorithm. Finally, in order to show the effectiveness of the proposed method, we show simulation examples by using real images, and result rate of detection is 85.0%.

AB - License plate recognition is very important in an automobile society. However, it is very difficult to do it, because a background and a body color of cars are similar to that of the license plate. Furthermore, the detection of cars in a moving at a very high-speed is difficult to be done. In this paper, we propose a new robust thresholds determination method in the various background by using the real coded genetic algorithm (RGA). By using RGA, the most likely plate colors are decided under various light conditions. First, the average brightness Y values of images are calculated. Next, relationship between the Y value and the most likely plate color thresholds (upper and lower bounds) are obtained by GA to estimate threshold equations by using the recursive least squares (RLS) algorithm. Finally, in order to show the effectiveness of the proposed method, we show simulation examples by using real images, and result rate of detection is 85.0%.

UR - http://www.scopus.com/inward/record.url?scp=0141795441&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0141795441&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0141795441

VL - 2

SP - 1227

EP - 1231

BT - Proceedings of the International Joint Conference on Neural Networks

ER -