The Study Of The License Plate Recognition Based On The Image Processing

The License Plate Recognition(LPR) system is the visual system whose goal is the License Plate. The license plate uniqueness makes the identification of a significant part of the realization of one of the its system. The car license automatic Recognition is the computer vision and the pattern recognition technology union.Along with automobile profession and mass transit enterprise development, the intelligent transportation control system changes essential.And it not only can widely be applied traffic flux detect, but also be applied to traffic control and lead. It can also be applied to some fields where the vehicle breaks the laws, such as airport, seaport, communities'vehicle manage, no halted vehicle's fee, and vehicle's safe. And intelligence transportation system include information gathering, picture processing and recognition, Automatic time and charge modules and so on .So it has widely applied in the future. In present paper main research intelligence transportation system based on picture processing steam car license recognition system.The following is the main content of the thesis:①At the License Plate image location and pick-up, proposed based on the pessimistic theory improvement seed localization algorithm. Then use Operator to Carry on to the car license region precisely locates. Finally goes to the false sign. Sobel②During the pretreatment phase. First uses the RemoveScatterNoise method. Then also proposed separately has carried on the adjustment to it in the vertical direction. Finally uses the level to revolve the method upwardly to carry on the adjustment in the horizontal side to the car license③On the course of incising the License Plate character.The thesis, firstly, brings forward coarsely incising the License Plate character.Then cutting the larger room than the License Plate character should lie in.④On the course of recognizing the License Plate character. The thesis minute divides into the car license character two parts of recognitions. The first part is the Chinese character are partial, uses the SVM vector machine method. The second part is the letter numeral are partial, the thesis brings forward to using the method of 13-character pick-up to pick up character of the License Plate character. Then we used the result to train the Backpropagation Network.Finally, we used the trained result to recognize the character and decided the result.According to the step that the thesis has taken, and the ways that we have taken brought before we write this.The experiment shows the result is effective.