Vehicle Type Identification Based on Car Tail Text Information.

摘要: Based on feature matching of car tail text information, a novel approach for vehicle identification is proposed in this paper. Our method creatively implements Scale-Invariant Feature Transform (SIFT) to extract distinctive invariant features from sub-images, which new application SIFT. In our approach, firstly, the coordinate and content vehicle’s license plate are presented during process localization recognition. Secondly, based location we apply information procedure could be divided into two processes, robust accurate localization. Then, SIFT-based template provided recognize information. Finally, able determine whether result conforms known type captured according contents vehicles file. The experimental results show high recognition rate acceptable time prove availability identification. Keywords-Scale-Invariant Transform; identification; information; image