A NOVEL CAR PLATE VERIFICATION WITH ADAPTIVE BINARIZATION METHOD

摘要：

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, Otsus 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.

关键词： Candidate verification License plate eztraction Image binarization Auto-Correlation Projection

作者: HUA-CHUN TAN HAO CHEN

作者单位: Department of Transportation Engineering, Beijing Institute of Technology, Beijing, China

会议类型: 国际会议

会议名称: 2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

会议地点: 昆明

会议语种:英文

页码: 4034-4039

在线出版日期: 2008-07-12（万方平台首次上网日期，不代表论文的发表时间）