Title :
A hybrid Macau license plate localization scheme based on vertical edge analysis
Author :
Yao, Wen-Li ; Pun, Chi-Man
Author_Institution :
Comput. & Inf. Sci. Dept., Univ. of Macau, Macau, China
Abstract :
This paper proposes an efficient method, the hybrid localization scheme, to solve the problem of Macau license plate localization. The approach is based on the edge analysis and statistics. Considering the characteristics of Macau license plates, proper edge analysis thresholds are acquired by statistics. The characteristics of black background and various rang of the ratio are added to the hierarchical scheme to determine the final location area. The experiment shows that the accuracy is improved a lot comparing to the previous methods.
Keywords :
edge detection; feature extraction; image colour analysis; traffic engineering computing; black background; edge analysis thresholds; edge statistics; hybrid Macau license plate localization scheme; vertical edge analysis; Cybernetics; Licenses; Machine learning; License plate extraction; edge detection; license plate localization; vertical edge analysis;
Conference_Titel :
Machine Learning and Cybernetics, 2009 International Conference on
Print_ISBN :
978-1-4244-3702-3
Electronic_ISBN :
978-1-4244-3703-0
DOI :
10.1109/ICMLC.2009.5212321
