Research On Location Methods For Vehicle License Plate Of Intelligent Transport System

Automatic vehicle-license-plate recognition system that is one part of Intelligent Transport System, is an attractive subject. This paper pays attention to the key part—vehicle-license-plate location. It does some deep research and attempts several methods. We hope to find some location methods that have high location accuracy and great computing speed by the research.Firstly, image is segmented by the method of fuzzy threshold, then genetic algorithm is used to search the license-plate in the segmented image with the help of the license-plate area feature. The experiment shows that this method is effective.Secondly, mathematical morphology and fractal are combined to locate the license-plate. After extracting the edge image with mathematical morphology, this paper locates the license-plate in the edge image by making use of fractal dimension.Thirdly, the location method of license-plate based on wavelet transform is researched. The wavelet transform has a good time-frequency feature. This feature can express the local feature of the original signal. This method applies wavelet transform to resolve a license-plate image, then segments the resolved image; based on the above two steps, the precise position of license-plate is confirmed by using the projection technique.Lastly, this paper summarizes the advantage and disadvantage of all above location methods. It also introduces some recognition methods of characters, the components and hardware of automatic vehicle-license-plate recognition system in brief.