Title :
An Approach to Horizontal Tilt Correction of Vehicle License Plate Based on Matchstick Model
Author :
Du, Yuren ; Wu, Zhenyu
Author_Institution :
Coll. of Inf. Eng., Yangzhou Univ., Yangzhou, China
Abstract :
Aiming at the problem of precision and real time in traditional methods to horizontal tilt correction of vehicle license plate, an approach based on matchstick model is presented. The principle is to get the correct license image from its tilt character line. A matchstick model is built up by abstracting the features of characters. By rotating the image with a certain degree, we can find whether it is horizontal with the matchstick model. Experimental results show that this method has high correction accuracy, less calculation and strong real time characteristics.
Keywords :
image recognition; vehicles; horizontal tilt correction; license image; matchstick model; vehicle license plate; Automotive engineering; Clustering methods; Color; Educational institutions; Feature extraction; Information science; Intelligent transportation systems; Licenses; Nearest neighbor searches; Vehicle detection;
Conference_Titel :
Information Science and Engineering (ICISE), 2009 1st International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4244-4909-5
DOI :
10.1109/ICISE.2009.239