Title :
A novel car plate verification with adaptive binarization method
Author :
Tan, Hua-Chun ; Chen, Hao
Author_Institution :
Dept. of Transp. Eng., Beijing Inst. of Technol., Beijing
Abstract :
A novel candidate verification algorithm for plate license localization is proposed in this paper. In the new method, auto-correlation curve, projection properties and character position features based on candidate binary image are combined together to verify the candidates. To improve the performance of verification, Otsupsilas method, Bersen method and Niblack method with post process are adaptive chosen to binarize images in different illumination. Experimental results show the efficiency of proposed method.
Keywords :
feature extraction; image recognition; Otsu method; adaptive binarization method; autocorrelation curve; car plate verification; character position features; plate license localization; Autocorrelation; Cybernetics; Frequency; Image segmentation; Intelligent control; Licenses; Lighting; Machine learning; Machine learning algorithms; Road transportation; Auto-Correlation; Candidate verification; Image binarization; License plate extraction; Projection;
Conference_Titel :
Machine Learning and Cybernetics, 2008 International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4244-2095-7
Electronic_ISBN :
978-1-4244-2096-4
DOI :
10.1109/ICMLC.2008.4621108
