A Multi-Style License Plate Verification Method Based on Character Classification under Illumination Variances
Zhongyan Liang, Jie Hu, Qiaojin Guo, Sanyuan Zhang
Available Online April 2016.
- https://doi.org/10.2991/emim-16.2016.165How to use a DOI?
- License plate verification; Spurious license plate classification; Spurious character classification; Principal Component Analysis; Support Vector Machines
- 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.
- Open Access
- This is an open access article distributed under the CC BY-NC license.
Cite this article
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 - 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 - https://doi.org/10.2991/emim-16.2016.165 ID - Liang2016/04 ER -