A Multi-Style License Plate Verification Method Based on Character Classification under Illumination Variances

DOI

10.2991/emim-16.2016.165How to use a DOI?

Keywords

License plate verification; Spurious license plate classification; Spurious character classification; Principal Component Analysis; Support Vector Machines

Abstract

License plate verification is essential for locating the license plate region precisely in a vehicle image. Existing verification methods implemented after location are effective for the single-style license plates, but will not do well when distinguishing multi-style ones from complex backgrounds. We propose a method based on segmented character classification, combining PCA and SVM, to deal with the verification of license plates with multi-style. Compared with previous methods, the segmented character regions can be analyzed more effectively, and the proposed method gets the high confidence level by calculating the classification result of the segmented characters but not the whole license plates. The experiments were done under complex illumination conditions, and the results show that the proposed method is effective for multi-style license plates for both fixed and moving camera systems.

Copyright

© 2016, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhongyan Liang
AU  - Jie Hu
AU  - Qiaojin Guo
AU  - Sanyuan Zhang
PY  - 2016/04
DA  - 2016/04
TI  - A Multi-Style License Plate Verification Method Based on Character Classification under Illumination Variances
BT  - Proceedings of the 6th International Conference on Electronic, Mechanical, Information and Management Society
PB  - Atlantis Press
SP  - 801
EP  - 806
SN  - 2352-538X
UR  - https://doi.org/10.2991/emim-16.2016.165
DO  - 10.2991/emim-16.2016.165
ID  - Liang2016/04
ER  -