Title :
License plate location based on adaboost
Author :
Zhang, Xiangdong ; Shen, Peiyi ; Bai, Jianhua ; Lei, Jing ; Hu, Yang ; Xiao, Yuli ; Li, Bo ; Qi, Dongpo
Author_Institution :
Xidian Univ., Xi´´an, China
Abstract :
License plate locating has been the bottleneck of Automatic Vehicle Recognition System. In order to improve the speed and accuracy of license plate locating, this paper proposes a simple and practical method of license plate locating. This method uses the adaboost algorithm to locate license plate. We can first enhance the texture features in the vertical direction of the plate through image preprocessing such as edge detection and binarization. And then, we can find out the horizontal region of license plate by counting the number of transitions from white pixel to black pixel. At last, we use the adaboost algorithm to locate the plate accurately.
Keywords :
edge detection; feature extraction; image recognition; traffic engineering computing; vehicles; adaboost algorithm; automatic vehicle recognition system; edge binarization; edge detection; image preprocessing; license plate location; Automation; Color; Computer vision; Gray-scale; Image edge detection; Iterative algorithms; Licenses; Neural networks; Pixel; Vehicle detection; adaboost algorithm; edge detection; license plate location; texture features;
Conference_Titel :
Information and Automation (ICIA), 2010 IEEE International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4244-5701-4
DOI :
10.1109/ICINFA.2010.5512232