Reliable license plate recognition by cascade classifier ensemble

Bailing Zhang; Hao Pan; Yang Li; Longfei Xu

doi:10.1007/978-81-322-1759-6_80

Reliable license plate recognition by cascade classifier ensemble

Bailing Zhang^*, Hao Pan, Yang Li, Longfei Xu

^*Corresponding author for this work

School of Advanced Technology

Xi'an Jiaotong-Liverpool University

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

2 Citations (Scopus)

Abstract

License Plate Recognition (LPR) is used in various security and traffic applications. This paper introduces a LPR system using morphological operations and edge detection for plate localization and characters segmentation. To emphasize the importance of classification reliability that is essential for reducing the cost caused by incorrect decisions, a cascaded classification system is designed, which consists of two modules, i.e., local mean k-nearest neighbor and one-versus-all support vector machine, each with reject option controlled by a properly defined reliability parameter. The impact of using the proposed cascade scheme is evaluated in terms of the trade-off between the rejection rate and classification accuracy. Experimental results confirm the effectiveness of the proposed system.

Original language	English
Title of host publication	International Conference on Computer Science and Information Technology, CSAIT 2013, Proceedings
Editors	Srikanta Patnaik, Xiaolong Li
Publisher	Springer Verlag
Pages	699-706
Number of pages	8
ISBN (Electronic)	9788132217589
DOIs	https://doi.org/10.1007/978-81-322-1759-6_80
Publication status	Published - 2014
Event	International Conference on Computer Science and Information Technology, CSAIT 2013 - Kunming, China Duration: 21 Sept 2013 → 23 Sept 2013

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	255
ISSN (Print)	2194-5357

Conference

Conference	International Conference on Computer Science and Information Technology, CSAIT 2013
Country/Territory	China
City	Kunming
Period	21/09/13 → 23/09/13

Keywords

Classification confidence
License plate recognition
Local mean k-nearest neighbor

Access to Document

10.1007/978-81-322-1759-6_80

Cite this

Zhang, B., Pan, H., Li, Y., & Xu, L. (2014). Reliable license plate recognition by cascade classifier ensemble. In S. Patnaik, & X. Li (Eds.), International Conference on Computer Science and Information Technology, CSAIT 2013, Proceedings (pp. 699-706). (Advances in Intelligent Systems and Computing; Vol. 255). Springer Verlag. https://doi.org/10.1007/978-81-322-1759-6_80

@inproceedings{03e065e7fa1649368a74754b6db6b670,

title = "Reliable license plate recognition by cascade classifier ensemble",

abstract = "License Plate Recognition (LPR) is used in various security and traffic applications. This paper introduces a LPR system using morphological operations and edge detection for plate localization and characters segmentation. To emphasize the importance of classification reliability that is essential for reducing the cost caused by incorrect decisions, a cascaded classification system is designed, which consists of two modules, i.e., local mean k-nearest neighbor and one-versus-all support vector machine, each with reject option controlled by a properly defined reliability parameter. The impact of using the proposed cascade scheme is evaluated in terms of the trade-off between the rejection rate and classification accuracy. Experimental results confirm the effectiveness of the proposed system.",

keywords = "Classification confidence, License plate recognition, Local mean k-nearest neighbor",

author = "Bailing Zhang and Hao Pan and Yang Li and Longfei Xu",

note = "Publisher Copyright: {\textcopyright} Springer India 2014.; International Conference on Computer Science and Information Technology, CSAIT 2013 ; Conference date: 21-09-2013 Through 23-09-2013",

year = "2014",

doi = "10.1007/978-81-322-1759-6_80",

language = "English",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer Verlag",

pages = "699--706",

editor = "Srikanta Patnaik and Xiaolong Li",

booktitle = "International Conference on Computer Science and Information Technology, CSAIT 2013, Proceedings",

}

Zhang, B, Pan, H, Li, Y & Xu, L 2014, Reliable license plate recognition by cascade classifier ensemble. in S Patnaik & X Li (eds), International Conference on Computer Science and Information Technology, CSAIT 2013, Proceedings. Advances in Intelligent Systems and Computing, vol. 255, Springer Verlag, pp. 699-706, International Conference on Computer Science and Information Technology, CSAIT 2013, Kunming, China, 21/09/13. https://doi.org/10.1007/978-81-322-1759-6_80

Reliable license plate recognition by cascade classifier ensemble. / Zhang, Bailing; Pan, Hao; Li, Yang et al.
International Conference on Computer Science and Information Technology, CSAIT 2013, Proceedings. ed. / Srikanta Patnaik; Xiaolong Li. Springer Verlag, 2014. p. 699-706 (Advances in Intelligent Systems and Computing; Vol. 255).

Research output: Chapter in Book or Report/Conference proceeding › Conference Proceeding › peer-review

TY - GEN

T1 - Reliable license plate recognition by cascade classifier ensemble

AU - Zhang, Bailing

AU - Pan, Hao

AU - Li, Yang

AU - Xu, Longfei

N1 - Publisher Copyright: © Springer India 2014.

PY - 2014

Y1 - 2014

N2 - License Plate Recognition (LPR) is used in various security and traffic applications. This paper introduces a LPR system using morphological operations and edge detection for plate localization and characters segmentation. To emphasize the importance of classification reliability that is essential for reducing the cost caused by incorrect decisions, a cascaded classification system is designed, which consists of two modules, i.e., local mean k-nearest neighbor and one-versus-all support vector machine, each with reject option controlled by a properly defined reliability parameter. The impact of using the proposed cascade scheme is evaluated in terms of the trade-off between the rejection rate and classification accuracy. Experimental results confirm the effectiveness of the proposed system.

AB - License Plate Recognition (LPR) is used in various security and traffic applications. This paper introduces a LPR system using morphological operations and edge detection for plate localization and characters segmentation. To emphasize the importance of classification reliability that is essential for reducing the cost caused by incorrect decisions, a cascaded classification system is designed, which consists of two modules, i.e., local mean k-nearest neighbor and one-versus-all support vector machine, each with reject option controlled by a properly defined reliability parameter. The impact of using the proposed cascade scheme is evaluated in terms of the trade-off between the rejection rate and classification accuracy. Experimental results confirm the effectiveness of the proposed system.

KW - Classification confidence

KW - License plate recognition

KW - Local mean k-nearest neighbor

UR - http://www.scopus.com/inward/record.url?scp=84927559314&partnerID=8YFLogxK

U2 - 10.1007/978-81-322-1759-6_80

DO - 10.1007/978-81-322-1759-6_80

M3 - Conference Proceeding

AN - SCOPUS:84927559314

T3 - Advances in Intelligent Systems and Computing

SP - 699

EP - 706

BT - International Conference on Computer Science and Information Technology, CSAIT 2013, Proceedings

A2 - Patnaik, Srikanta

A2 - Li, Xiaolong

PB - Springer Verlag

T2 - International Conference on Computer Science and Information Technology, CSAIT 2013

Y2 - 21 September 2013 through 23 September 2013

ER -

Reliable license plate recognition by cascade classifier ensemble

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this