A Novel method for license plate location

DOI

10.2991/amcce-18.2018.133How to use a DOI?

Keywords

license plate, Sobel filter, hsv colour space.

Abstract

license plate location is one of the key steps for license plate recognition. With license plate recognition technology, police can better manage vehicle and this technique also give convenience to application such as parking fee charge. In this paper, we propose a novel method to locate license plate of china in complicate environment. First, we change the RGB image into grey-scale image. Then, we apply Sobel operator on the grey-scale image to get its Sobel edge image. After that the Sobel edge image is change into a binary image in which each pixels of the image are decided by statistic its variance in nearby vertical and horizontal pixels. Base on the binary image above, the algorithm locates the candidate boxes and produces a list for them. Next, we select the boxes above by using hsv colour space and then merge the boxes base on their location. At last, the unreasonable boxes are removed and the final location of license plates produced. Our method has outperformed two types of license plate location products in a small surveillance dataset and achieved a fast and high precision location result compared with the-state-of-art.

Copyright

© 2018, 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  - Jiawen Song
AU  - Chuang Zhu
AU  - Xiaodong Xie
AU  - Yuan Li
AU  - Meng Wang
AU  - Huizhu Jia
PY  - 2018/05
DA  - 2018/05
TI  - A Novel method for license plate location
BT  - Proceedings of the 2018 3rd International Conference on Automation, Mechanical Control and Computational Engineering (AMCCE 2018)
PB  - Atlantis Press
SP  - 762
EP  - 767
SN  - 2352-5401
UR  - https://doi.org/10.2991/amcce-18.2018.133
DO  - 10.2991/amcce-18.2018.133
ID  - Song2018/05
ER  -