Research On The Key Techniques Of License Plate Recognition

The research and development of license plate recognition system are hot topics in modern traffic development and determine the intelligentization and modernization of traffic system.The paper has gone deep into every step of LPR relatively, the main research work of this thesis is presented as follows:1. License plate location: The paper adopt a location method, which based on the region shape of plate and the grey change property.First, the method separated the sub-image of containing license plate, accomplishing the coarse location, and then dealed with the sub-image, accomplishing the accurate location.The experimental results show that the algorithm is able to extract license plate field quickly and efficiently.2. Character segmentation: The paper used incline-revising and rim-cleaning method to eliminate the disturbed factors mostly.Singled character is picked out by projection method combining with the transcendent information.3. Character recognition: According to the different configuration of Chinese character and number, letter character, the paper used different method to regconize characters: improved template matching method for Chinese character recognition, method based on the configuration property for number and letter character recognition.The experimental results are good.On the basic of before-mentioned research, the paper designed and implemented a emulational LPR System.