The research and development on vehicle license plate recognitionsystem are hot topics in modern traffic development and also areimportant elements determining the intelligentization and modernizationof traffic system.The location and segmentation of vehicle license plateis one of the most pivotal technology in the recognition system.It isa base of character segmentation and recognition and it plays a crucialrole in the performance of the whole system.Towards this pivotal question,this paper summarizes an algorithmintegrating edge detection and iterative thresholding,based onextensive analyses and comparison of the existing algorithms.Then thealgorithm is used to binarize the image.Furthermore,on the base ofimprovement towards the traditional projection,the location andsegmentation of vehicle license plate is realized.The experimental results indicate that the experimental algorithmin this paper is more effective and more precise.It has the advantagethat this algorithm remains the edge of the license plate and makeslicense plate different from the background as possible as it can.Thereis a more evident result when it is used to process the image of staticvehicles.So it is fit for being applied to the locations such as car-parksand toll-stations.In this paper,some researches about the location and segmentationof vehicle license plate have been done.But there still is a long wayfor them to go before being applied to practical applications.They needto be further studied and improved in the future.
|