Study on License Plate Recognition Technology Based on Visual Characteristics

In this paper, the license plate recognition, in the case of the character´s local information missing and the license plate partially obstructed, is taken as the research objective. According to the visual identification features that the overall message can be inferred from local information, the characters whose local information missing in the license plate can be deduced from the local evidence which is obtained though meshing characters, and the license plate partially obstructed can be identified through the fusion of multi-frame local information in the sequence images with the serial correlation method. Experiments show that the recognition algorithm can be applied effectively to identify the characters whose local information missing and the license plate partially obstructed.