A new reliable approach for Persian license plate detection on colour images

Amir Hossein Ashtari, Md. Jan Nordin, Seyed Mostafa Mousavi Kahaki

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

9 Citations (Scopus)

Abstract

In this paper, a new approach for car license plate detection will be presented. The proposed method is faster than previous methods as it avoids time-consuming image transformations such as Hough transform, Fourier transform, wavelet transform, etc. The suggested method is based on modified mathematical template matching and colour analysis to detect the location of the car's plate. This new method detects all plates in a matching cycle using avoidance dynamic templates such as classic template matching methods, neural network, PCI based and other artificial intelligence matching methods. A modified column strip search to find a standard geometrical template in new types of license plates in Iran and most European countries has been proposed. Some advantages of this method are: high-speed process/ low response time, ability to setup and run on microprocessors and process colour images without any resizing and converting. The suggested method can be used in automatic toll stations, tunnels, high ways, intelligent parking and traffic zone areas as a real-time license plate recognition system. Plate characters are recognized by a Support Vector Machine with a homogeneous polynomial kernel of degree five. The results of experiments based on images from speed control cameras on high ways demonstrate the performance, exactness, speed and reliability of this method. Finally, the proposed method boasts 96 percent performance detection rate.

Original languageEnglish
Title of host publicationProceedings of the 2011 International Conference on Electrical Engineering and Informatics, ICEEI 2011
DOIs
Publication statusPublished - 2011
Event2011 International Conference on Electrical Engineering and Informatics, ICEEI 2011 - Bandung
Duration: 17 Jul 201119 Jul 2011

Other

Other2011 International Conference on Electrical Engineering and Informatics, ICEEI 2011
CityBandung
Period17/7/1119/7/11

Fingerprint

Template matching
Railroad cars
Color
Hough transforms
Parking
Speed control
Wavelet transforms
Artificial intelligence
Support vector machines
Microprocessor chips
Fourier transforms
Tunnels
Cameras
Polynomials
Neural networks
Experiments

Keywords

  • geometrical template matching
  • license plate detection
  • license plate localization
  • license plate recognition
  • LPR

ASJC Scopus subject areas

  • Information Systems
  • Electrical and Electronic Engineering

Cite this

Ashtari, A. H., Nordin, M. J., & Kahaki, S. M. M. (2011). A new reliable approach for Persian license plate detection on colour images. In Proceedings of the 2011 International Conference on Electrical Engineering and Informatics, ICEEI 2011 [6021697] https://doi.org/10.1109/ICEEI.2011.6021697

A new reliable approach for Persian license plate detection on colour images. / Ashtari, Amir Hossein; Nordin, Md. Jan; Kahaki, Seyed Mostafa Mousavi.

Proceedings of the 2011 International Conference on Electrical Engineering and Informatics, ICEEI 2011. 2011. 6021697.

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

Ashtari, AH, Nordin, MJ & Kahaki, SMM 2011, A new reliable approach for Persian license plate detection on colour images. in Proceedings of the 2011 International Conference on Electrical Engineering and Informatics, ICEEI 2011., 6021697, 2011 International Conference on Electrical Engineering and Informatics, ICEEI 2011, Bandung, 17/7/11. https://doi.org/10.1109/ICEEI.2011.6021697
Ashtari AH, Nordin MJ, Kahaki SMM. A new reliable approach for Persian license plate detection on colour images. In Proceedings of the 2011 International Conference on Electrical Engineering and Informatics, ICEEI 2011. 2011. 6021697 https://doi.org/10.1109/ICEEI.2011.6021697
Ashtari, Amir Hossein ; Nordin, Md. Jan ; Kahaki, Seyed Mostafa Mousavi. / A new reliable approach for Persian license plate detection on colour images. Proceedings of the 2011 International Conference on Electrical Engineering and Informatics, ICEEI 2011. 2011.
@inproceedings{6c2cdbd084bb4757b78fd073b504050f,
title = "A new reliable approach for Persian license plate detection on colour images",
abstract = "In this paper, a new approach for car license plate detection will be presented. The proposed method is faster than previous methods as it avoids time-consuming image transformations such as Hough transform, Fourier transform, wavelet transform, etc. The suggested method is based on modified mathematical template matching and colour analysis to detect the location of the car's plate. This new method detects all plates in a matching cycle using avoidance dynamic templates such as classic template matching methods, neural network, PCI based and other artificial intelligence matching methods. A modified column strip search to find a standard geometrical template in new types of license plates in Iran and most European countries has been proposed. Some advantages of this method are: high-speed process/ low response time, ability to setup and run on microprocessors and process colour images without any resizing and converting. The suggested method can be used in automatic toll stations, tunnels, high ways, intelligent parking and traffic zone areas as a real-time license plate recognition system. Plate characters are recognized by a Support Vector Machine with a homogeneous polynomial kernel of degree five. The results of experiments based on images from speed control cameras on high ways demonstrate the performance, exactness, speed and reliability of this method. Finally, the proposed method boasts 96 percent performance detection rate.",
keywords = "geometrical template matching, license plate detection, license plate localization, license plate recognition, LPR",
author = "Ashtari, {Amir Hossein} and Nordin, {Md. Jan} and Kahaki, {Seyed Mostafa Mousavi}",
year = "2011",
doi = "10.1109/ICEEI.2011.6021697",
language = "English",
isbn = "9781457707520",
booktitle = "Proceedings of the 2011 International Conference on Electrical Engineering and Informatics, ICEEI 2011",

}

TY - GEN

T1 - A new reliable approach for Persian license plate detection on colour images

AU - Ashtari, Amir Hossein

AU - Nordin, Md. Jan

AU - Kahaki, Seyed Mostafa Mousavi

PY - 2011

Y1 - 2011

N2 - In this paper, a new approach for car license plate detection will be presented. The proposed method is faster than previous methods as it avoids time-consuming image transformations such as Hough transform, Fourier transform, wavelet transform, etc. The suggested method is based on modified mathematical template matching and colour analysis to detect the location of the car's plate. This new method detects all plates in a matching cycle using avoidance dynamic templates such as classic template matching methods, neural network, PCI based and other artificial intelligence matching methods. A modified column strip search to find a standard geometrical template in new types of license plates in Iran and most European countries has been proposed. Some advantages of this method are: high-speed process/ low response time, ability to setup and run on microprocessors and process colour images without any resizing and converting. The suggested method can be used in automatic toll stations, tunnels, high ways, intelligent parking and traffic zone areas as a real-time license plate recognition system. Plate characters are recognized by a Support Vector Machine with a homogeneous polynomial kernel of degree five. The results of experiments based on images from speed control cameras on high ways demonstrate the performance, exactness, speed and reliability of this method. Finally, the proposed method boasts 96 percent performance detection rate.

AB - In this paper, a new approach for car license plate detection will be presented. The proposed method is faster than previous methods as it avoids time-consuming image transformations such as Hough transform, Fourier transform, wavelet transform, etc. The suggested method is based on modified mathematical template matching and colour analysis to detect the location of the car's plate. This new method detects all plates in a matching cycle using avoidance dynamic templates such as classic template matching methods, neural network, PCI based and other artificial intelligence matching methods. A modified column strip search to find a standard geometrical template in new types of license plates in Iran and most European countries has been proposed. Some advantages of this method are: high-speed process/ low response time, ability to setup and run on microprocessors and process colour images without any resizing and converting. The suggested method can be used in automatic toll stations, tunnels, high ways, intelligent parking and traffic zone areas as a real-time license plate recognition system. Plate characters are recognized by a Support Vector Machine with a homogeneous polynomial kernel of degree five. The results of experiments based on images from speed control cameras on high ways demonstrate the performance, exactness, speed and reliability of this method. Finally, the proposed method boasts 96 percent performance detection rate.

KW - geometrical template matching

KW - license plate detection

KW - license plate localization

KW - license plate recognition

KW - LPR

UR - http://www.scopus.com/inward/record.url?scp=80054016133&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80054016133&partnerID=8YFLogxK

U2 - 10.1109/ICEEI.2011.6021697

DO - 10.1109/ICEEI.2011.6021697

M3 - Conference contribution

SN - 9781457707520

BT - Proceedings of the 2011 International Conference on Electrical Engineering and Informatics, ICEEI 2011

ER -