Macau License Plate Character Segmentation Through ROI detection and Redundant Region Removal Method

Bingshu Wang; Yin Ping Zhao; Jiangbin Zheng; Shuang Feng

doi:10.1109/ICISFall51598.2021.9627479

Macau License Plate Character Segmentation Through ROI detection and Redundant Region Removal Method

Bingshu Wang, Yin Ping Zhao, Jiangbin Zheng, Shuang Feng

School of Software

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

Abstract

License plate character segmentation links the function between license plate detection module and character recognition module. Variable-length license plate character segmentation is a challenging task due to the variations of license plate styles. In this paper, our work is focused on the character segmentation task. It is based on the detection results of 'Region of Interest(ROI)' detection method. The main contributions include two parts. Firstly, a reference region is estimated according to candidate regions by median statistics of width and height. The reference region is used to compare with all the candidate regions, aiming to remove false positives. Secondly, a redundant region removal method is proposed. It is implemented by removing cross regions which are located at the same location of character. Experimental results on Macau license plates show that the proposed method achieves promising results with 99.37 % segmentation accuracy.

Original language	English
Title of host publication	Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall
Editors	Kailong Zhang, Qun Chen, Jiangbin Zheng, Simon Xu, Rei Zhang, Wencai Du, Shigang Li
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	121-125
Number of pages	5
ISBN (Electronic)	9781728176796
DOIs	https://doi.org/10.1109/ICISFall51598.2021.9627479
State	Published - 2021
Event	21st IEEE/ACIS International Fall Conference on Computer and Information Science, ICIS 2021-Fall - Xi�an, China Duration: 13 Oct 2021 → 15 Oct 2021

Publication series

Name	Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall

Conference

Conference	21st IEEE/ACIS International Fall Conference on Computer and Information Science, ICIS 2021-Fall
Country/Territory	China
City	Xi�an
Period	13/10/21 → 15/10/21

Keywords

Character segmentation
Redundant region removal
ROI-based detection
Variable-length license plate

Access to Document

10.1109/ICISFall51598.2021.9627479

Cite this

Wang, B., Zhao, Y. P., Zheng, J., & Feng, S. (2021). Macau License Plate Character Segmentation Through ROI detection and Redundant Region Removal Method. In K. Zhang, Q. Chen, J. Zheng, S. Xu, R. Zhang, W. Du, & S. Li (Eds.), Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall (pp. 121-125). (Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICISFall51598.2021.9627479

Wang, Bingshu ; Zhao, Yin Ping ; Zheng, Jiangbin et al. / Macau License Plate Character Segmentation Through ROI detection and Redundant Region Removal Method. Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall. editor / Kailong Zhang ; Qun Chen ; Jiangbin Zheng ; Simon Xu ; Rei Zhang ; Wencai Du ; Shigang Li. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 121-125 (Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall).

@inproceedings{3b73a6c980e4467db8cd3afb8fe4288c,

title = "Macau License Plate Character Segmentation Through ROI detection and Redundant Region Removal Method",

abstract = "License plate character segmentation links the function between license plate detection module and character recognition module. Variable-length license plate character segmentation is a challenging task due to the variations of license plate styles. In this paper, our work is focused on the character segmentation task. It is based on the detection results of 'Region of Interest(ROI)' detection method. The main contributions include two parts. Firstly, a reference region is estimated according to candidate regions by median statistics of width and height. The reference region is used to compare with all the candidate regions, aiming to remove false positives. Secondly, a redundant region removal method is proposed. It is implemented by removing cross regions which are located at the same location of character. Experimental results on Macau license plates show that the proposed method achieves promising results with 99.37 % segmentation accuracy.",

keywords = "Character segmentation, Redundant region removal, ROI-based detection, Variable-length license plate",

author = "Bingshu Wang and Zhao, {Yin Ping} and Jiangbin Zheng and Shuang Feng",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 21st IEEE/ACIS International Fall Conference on Computer and Information Science, ICIS 2021-Fall ; Conference date: 13-10-2021 Through 15-10-2021",

year = "2021",

doi = "10.1109/ICISFall51598.2021.9627479",

language = "英语",

series = "Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "121--125",

editor = "Kailong Zhang and Qun Chen and Jiangbin Zheng and Simon Xu and Rei Zhang and Wencai Du and Shigang Li",

booktitle = "Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall",

}

Wang, B, Zhao, YP, Zheng, J & Feng, S 2021, Macau License Plate Character Segmentation Through ROI detection and Redundant Region Removal Method. in K Zhang, Q Chen, J Zheng, S Xu, R Zhang, W Du & S Li (eds), Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall. Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall, Institute of Electrical and Electronics Engineers Inc., pp. 121-125, 21st IEEE/ACIS International Fall Conference on Computer and Information Science, ICIS 2021-Fall, Xi�an, China, 13/10/21. https://doi.org/10.1109/ICISFall51598.2021.9627479

Macau License Plate Character Segmentation Through ROI detection and Redundant Region Removal Method. / Wang, Bingshu; Zhao, Yin Ping; Zheng, Jiangbin et al.
Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall. ed. / Kailong Zhang; Qun Chen; Jiangbin Zheng; Simon Xu; Rei Zhang; Wencai Du; Shigang Li. Institute of Electrical and Electronics Engineers Inc., 2021. p. 121-125 (Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall).

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

TY - GEN

T1 - Macau License Plate Character Segmentation Through ROI detection and Redundant Region Removal Method

AU - Wang, Bingshu

AU - Zhao, Yin Ping

AU - Zheng, Jiangbin

AU - Feng, Shuang

PY - 2021

Y1 - 2021

N2 - License plate character segmentation links the function between license plate detection module and character recognition module. Variable-length license plate character segmentation is a challenging task due to the variations of license plate styles. In this paper, our work is focused on the character segmentation task. It is based on the detection results of 'Region of Interest(ROI)' detection method. The main contributions include two parts. Firstly, a reference region is estimated according to candidate regions by median statistics of width and height. The reference region is used to compare with all the candidate regions, aiming to remove false positives. Secondly, a redundant region removal method is proposed. It is implemented by removing cross regions which are located at the same location of character. Experimental results on Macau license plates show that the proposed method achieves promising results with 99.37 % segmentation accuracy.

AB - License plate character segmentation links the function between license plate detection module and character recognition module. Variable-length license plate character segmentation is a challenging task due to the variations of license plate styles. In this paper, our work is focused on the character segmentation task. It is based on the detection results of 'Region of Interest(ROI)' detection method. The main contributions include two parts. Firstly, a reference region is estimated according to candidate regions by median statistics of width and height. The reference region is used to compare with all the candidate regions, aiming to remove false positives. Secondly, a redundant region removal method is proposed. It is implemented by removing cross regions which are located at the same location of character. Experimental results on Macau license plates show that the proposed method achieves promising results with 99.37 % segmentation accuracy.

KW - Character segmentation

KW - Redundant region removal

KW - ROI-based detection

KW - Variable-length license plate

UR - http://www.scopus.com/inward/record.url?scp=85123600162&partnerID=8YFLogxK

U2 - 10.1109/ICISFall51598.2021.9627479

DO - 10.1109/ICISFall51598.2021.9627479

M3 - 会议稿件

AN - SCOPUS:85123600162

T3 - Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall

SP - 121

EP - 125

BT - Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall

A2 - Zhang, Kailong

A2 - Chen, Qun

A2 - Zheng, Jiangbin

A2 - Xu, Simon

A2 - Zhang, Rei

A2 - Du, Wencai

A2 - Li, Shigang

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 21st IEEE/ACIS International Fall Conference on Computer and Information Science, ICIS 2021-Fall

Y2 - 13 October 2021 through 15 October 2021

ER -

Wang B, Zhao YP, Zheng J, Feng S. Macau License Plate Character Segmentation Through ROI detection and Redundant Region Removal Method. In Zhang K, Chen Q, Zheng J, Xu S, Zhang R, Du W, Li S, editors, Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall. Institute of Electrical and Electronics Engineers Inc. 2021. p. 121-125. (Proceedings - 2021 IEEE/ACIS 21st International Fall Conference on Computer and Information Science, ICIS 2021-Fall). doi: 10.1109/ICISFall51598.2021.9627479

Macau License Plate Character Segmentation Through ROI detection and Redundant Region Removal Method

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this