License Plate Number Recognition System To Achieve

The essential technology of the recognition of License plate recognition system lies in the digital image pretreatment technology, the plate location technology and the intelligent character recognition technology. The paper applies the plate location technology, the image calibration technology, the character division technology, the license character recognition technology based on SVM and structural features to the LPR system. By considering the processes of the vehicle's license plate identification, screening methods and algorithms according to the demands of each link function, the paper makes a comparative analysis of the key links and algorithms by experiments, and the related algorithms are improved or some new algorithms were put forward. This thesis is mainly about the following four Parts:Firstly, the license plate location algorithm for a bold attempt to sum up the methods proposed by their predecessors and a large number of tests, a projection based on mathematical morphology and a combination of license plate location algorithm, accurate and rapid positioning of the location of vehicle brands .Secondly, the image correction technology in conducting research for this paper, Hough transform-based detection and correction angle method. In this paper, the license plate number of a wide range of tilt angle calculation means to conduct a large number of experiments, the final choice point by calculating the characters to determine the angle of inclination of the plate. Which occurred in the context of inclined plates or more complex images of license plates can be divided correctly.Third, segmentation of the characters in conducting research based on the projection method and the method of fitting a straight line. This method can effectively remove the image of the frame, license plate rivets and other interference, and can effectively partition the correct characters.Finally, character recognition, in order to reduce the computational complexity is proposed in this paper support vector machines with characteristics in accordance with a combination of character recognition methods have achieved good results.As a result,it Proves that this recognition system can be relatively accurate to locate license plate and recognize characters and the Performance of the system is good. It shows that combined pretreatments and recognition techniques can improve the ability of recognition.