Title :
Research on character segmentation in license plate recognition
Author :
Li, Xiaoping ; Ling, Feng ; Lv, Xiaoxing ; Li, Yinxiang ; Xu, Jianqiang
Author_Institution :
Dept. of Comput. Sci. & Technol., Beijing Inst. of Technol., Beijing, China
Abstract :
License plate recognition can be widely used in traffic direction of Olympic Games, traffic management, and so on. Because the picture of license plate is complex, the character segmentation error is a main cause of decrease of license plate recognition rate. Research on denoising and character segmentation algorithm is crucial in the license plate recognition system. Connected domain analysis method, segmentation projection histogram method and shelling projection method are discussed and the improved methods are proposed according to shortcomings of each methods.
Keywords :
image segmentation; optical character recognition; Olympic games; character segmentation; connected domain analysis method; license plate recognition; segmentation projection histogram method; shelling projection method; traffic direction; traffic management; Algorithm design and analysis; Character recognition; Computer errors; Computer science; Histograms; Image recognition; Image segmentation; Licenses; Noise reduction; Technology management; character segmentation; connected domain analysis; license plate recognition; segmentation projection; shelling projection;
Conference_Titel :
New Trends in Information Science and Service Science (NISS), 2010 4th International Conference on
Conference_Location :
Gyeongju
Print_ISBN :
978-1-4244-6982-6
Electronic_ISBN :
978-89-88678-17-6
