Paper Info
Title
An Algorithm Combined with Color Differential Models for License-Plate Location.
Abstract
Vehicle license plate recognition technology is one of the core technologies of intelligent transportation systems. The first and most important step in the entire license plate recognition system is positioning the license plate. The positioning accuracy will directly influence the subsequent segmentation and recognition accuracy. This paper presents a new adaboost algorithm combined with color differential model. First, we introduce the process of calculation of the color differential model. Second, we give a full distribution about the adaboost algorithm combined with color differential model. At last, we analyze the results of the algorithm based on RGB color model and give a comparison between the adaboost algorithm combined with the new feature and other license plate location algorithms. This novel adaboost algorithm overcomes the problems of license plate location algorithms based on color information, such as the sensitivity to light and the difficulty to locate license plates in complex background and so on. The experimental results show that the novel adaboost algorithm combined with color differential model is timeliness and robustness. At night, the precision rate of the novel adaboost algorithm can attain above 95.0%.
Year
DOI
Venue
2015
10.1007/978-3-662-48570-5_41
Communications in Computer and Information Science
Keywords
Field
DocType
License plate location,Color differential model,Adaboost algorithm
Adaboost algorithm,Recognition system,Segmentation,Computer science,Algorithm,Robustness (computer science),RGB color model,Intelligent transportation system,License
Conference
Volume
ISSN
Citations 
547
1865-0929
1
PageRank 
References 
Authors
0.36
3
8
Name
Order
Citations
PageRank
Xiangdong Zhang110.36
Peiyi Shen221719.72
Juan Song321.04
Liang Zhang46410.30
Weibin Gong510.36
Wei Wei650768.07
Yuanmei Tian710.70
Zhu, G.88312.50