A Robust Character Segmentation Algorithm for Chinese License Plate

摘要：

License plate character segmentation is a crucial phrase in license plate recognition (LPR) system. A robust algorithm for character segmentation of vehicle license plates is presented in this paper. Firstly,plate image preprocessing,such as image binarization and horizontal frame removing,is performed on the license plate. Secondly,characters are divided by means of vertical projection and connected components analysis (CCA). Finally,characters-matching is used to decide which segmented parts would be the plate characters. Experimental results show that the proposed method can achieve a high correct rate under bad conditions.

关键词： character segmentation global and local binarization projection segmentation connected components analysis

作者: Wei Luo Yong Zhao Yule Yuan Jingwei Liu Wei Fang

作者单位: The Key Laboratory of Integrated Microsystems,Shenzhen Graduate School,Peking University,Shenzhen,China

会议类型: 国际会议

会议名称: 2011 International Conference on Opto-Electronics Engineering and Information Science(2011光电电子工程与信息科学国际会议 ICOEIS 2011)

会议地点: 西安

会议语种:英文

页码: 221-227

在线出版日期: 2011-12-23（万方平台首次上网日期，不代表论文的发表时间）