The Research Of The Vehicle License Plate Automatic Recognition Technology Based On Wavelet Transform And RBF Neural Network

In recent years, image processing, communications technology and computer technology have received widespread applications in the field of transportation. Plate recognition technology is one of the hottest researches among them, plate recognition technology is widely used in the crossing fees system and traffic management system. It has received enormous economic and practical value.A typical vehicle License-Plate Recognition system including vehicle License-Plate image locating, characters extraction and characters recognition.The paper presents some means for these problem, so that the system can efficiently accomplish character Recognition.License locating is the difficulty of the license plate automatic recognition.The locating time and accuracy directly impact the license plate system's recognition performance. The author presents a new method base on wavelet transform in the locating of license plates.The license plate image can be detected and located using wavelet transform.The experiment indicates that compared with other methods, this method has greatly improved the locating accuracy.Vehicle License-Plate characters extraction is the most difficult of this system, the paper uses the wavelet transform method has effectively improved the complex environments vehicle License-Plate locating and extracting license plate.At the same time, this paper has also researched characters recognition of this system. A new character recognition algorithm is presented, which combines the method using topology characteristics of characters and the method of RBF neural network. High recognition accuracy is reached.