Learning-based approach for license plate recognition

Kap Kee Kim, Jong Bae Kim, Kwang In Kim, Hang Joon Kim

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

127 Citations (Scopus)

Abstract

Presents a learning-based approach for the construction of a license-plate recognition system. The system consists of three modules. They are, respectively, the car detection module, the license-plate segmentation module and the recognition module. The car detection module detects a car in a given image sequence obtained from a camera with a simple color-based approach. The segmentation module extracts the license plate in the detected car image using neural networks as filters for analyzing the color and texture properties of the license plate. The recognition module then reads the characters on the detected license plate with a support vector machine (SVM)-based character recognizer. The system has been tested with 1000 video sequences obtained from toll-gates, parking lots, etc., and has shown the following performances on average: car detection rate 100%, segmentation rate 97.5%, and character recognition rate about 97.2%.
Original languageEnglish
Title of host publicationNeural Networks for Signal Processing X, 2000
Subtitle of host publicationProc. IEEE International Workshop on Neural Networks for Signal Processing, 2000. Volume 2
EditorsB. Widrow, J. Larsen, L. Guan, E. Wilson, K. Paliwa, S. Douglas, T. Adali
PublisherIEEE
Pages614-623
Number of pages10
ISBN (Print)9780780362789
DOIs
Publication statusPublished - 31 Jan 2001

Fingerprint

Railroad cars
Color
Character recognition
Parking
Support vector machines
Textures
Cameras
Neural networks

Cite this

Kim, K. K., Kim, J. B., Kim, K. I., & Kim, H. J. (2001). Learning-based approach for license plate recognition. In B. Widrow, J. Larsen, L. Guan, E. Wilson, K. Paliwa, S. Douglas, & T. Adali (Eds.), Neural Networks for Signal Processing X, 2000: Proc. IEEE International Workshop on Neural Networks for Signal Processing, 2000. Volume 2 (pp. 614-623). IEEE. https://doi.org/10.1109/NNSP.2000.890140

Learning-based approach for license plate recognition. / Kim, Kap Kee; Kim, Jong Bae; Kim, Kwang In; Kim, Hang Joon .

Neural Networks for Signal Processing X, 2000: Proc. IEEE International Workshop on Neural Networks for Signal Processing, 2000. Volume 2. ed. / B. Widrow; J. Larsen; L. Guan; E. Wilson; K. Paliwa; S. Douglas; T. Adali. IEEE, 2001. p. 614-623.

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

Kim, KK, Kim, JB, Kim, KI & Kim, HJ 2001, Learning-based approach for license plate recognition. in B Widrow, J Larsen, L Guan, E Wilson, K Paliwa, S Douglas & T Adali (eds), Neural Networks for Signal Processing X, 2000: Proc. IEEE International Workshop on Neural Networks for Signal Processing, 2000. Volume 2. IEEE, pp. 614-623. https://doi.org/10.1109/NNSP.2000.890140
Kim KK, Kim JB, Kim KI, Kim HJ. Learning-based approach for license plate recognition. In Widrow B, Larsen J, Guan L, Wilson E, Paliwa K, Douglas S, Adali T, editors, Neural Networks for Signal Processing X, 2000: Proc. IEEE International Workshop on Neural Networks for Signal Processing, 2000. Volume 2. IEEE. 2001. p. 614-623 https://doi.org/10.1109/NNSP.2000.890140
Kim, Kap Kee ; Kim, Jong Bae ; Kim, Kwang In ; Kim, Hang Joon . / Learning-based approach for license plate recognition. Neural Networks for Signal Processing X, 2000: Proc. IEEE International Workshop on Neural Networks for Signal Processing, 2000. Volume 2. editor / B. Widrow ; J. Larsen ; L. Guan ; E. Wilson ; K. Paliwa ; S. Douglas ; T. Adali. IEEE, 2001. pp. 614-623
@inproceedings{f8574b44ad5b41e58e802fd415067959,
title = "Learning-based approach for license plate recognition",
abstract = "Presents a learning-based approach for the construction of a license-plate recognition system. The system consists of three modules. They are, respectively, the car detection module, the license-plate segmentation module and the recognition module. The car detection module detects a car in a given image sequence obtained from a camera with a simple color-based approach. The segmentation module extracts the license plate in the detected car image using neural networks as filters for analyzing the color and texture properties of the license plate. The recognition module then reads the characters on the detected license plate with a support vector machine (SVM)-based character recognizer. The system has been tested with 1000 video sequences obtained from toll-gates, parking lots, etc., and has shown the following performances on average: car detection rate 100{\%}, segmentation rate 97.5{\%}, and character recognition rate about 97.2{\%}.",
author = "Kim, {Kap Kee} and Kim, {Jong Bae} and Kim, {Kwang In} and Kim, {Hang Joon}",
year = "2001",
month = "1",
day = "31",
doi = "10.1109/NNSP.2000.890140",
language = "English",
isbn = "9780780362789",
pages = "614--623",
editor = "B. Widrow and J. Larsen and L. Guan and E. Wilson and K. Paliwa and S. Douglas and T. Adali",
booktitle = "Neural Networks for Signal Processing X, 2000",
publisher = "IEEE",
address = "USA United States",

}

TY - GEN

T1 - Learning-based approach for license plate recognition

AU - Kim, Kap Kee

AU - Kim, Jong Bae

AU - Kim, Kwang In

AU - Kim, Hang Joon

PY - 2001/1/31

Y1 - 2001/1/31

N2 - Presents a learning-based approach for the construction of a license-plate recognition system. The system consists of three modules. They are, respectively, the car detection module, the license-plate segmentation module and the recognition module. The car detection module detects a car in a given image sequence obtained from a camera with a simple color-based approach. The segmentation module extracts the license plate in the detected car image using neural networks as filters for analyzing the color and texture properties of the license plate. The recognition module then reads the characters on the detected license plate with a support vector machine (SVM)-based character recognizer. The system has been tested with 1000 video sequences obtained from toll-gates, parking lots, etc., and has shown the following performances on average: car detection rate 100%, segmentation rate 97.5%, and character recognition rate about 97.2%.

AB - Presents a learning-based approach for the construction of a license-plate recognition system. The system consists of three modules. They are, respectively, the car detection module, the license-plate segmentation module and the recognition module. The car detection module detects a car in a given image sequence obtained from a camera with a simple color-based approach. The segmentation module extracts the license plate in the detected car image using neural networks as filters for analyzing the color and texture properties of the license plate. The recognition module then reads the characters on the detected license plate with a support vector machine (SVM)-based character recognizer. The system has been tested with 1000 video sequences obtained from toll-gates, parking lots, etc., and has shown the following performances on average: car detection rate 100%, segmentation rate 97.5%, and character recognition rate about 97.2%.

UR - http://dx.doi.org/10.1109/NNSP.2000.890140

U2 - 10.1109/NNSP.2000.890140

DO - 10.1109/NNSP.2000.890140

M3 - Conference contribution

SN - 9780780362789

SP - 614

EP - 623

BT - Neural Networks for Signal Processing X, 2000

A2 - Widrow, B.

A2 - Larsen, J.

A2 - Guan, L.

A2 - Wilson, E.

A2 - Paliwa, K.

A2 - Douglas, S.

A2 - Adali, T.

PB - IEEE

ER -