License Plate Recognition Research And Implementation

With the socio-economic development and people's standard of living are general improving, the requirement of the whole society's transport are increasing, traffic has become more and more congestion. It has put great pressure on society and the environment. Intelligent Transportation Systems (ITS) is the main way to solve the phenomenons of traffic congestion and blocking.License plate recognition system (LPR) is the key technology of ITS. It been gradually applied in our real life. LPR can automatically register, verificate, monitor and alarm, it has been applied to road traffic management, toll highway network, electronic police, parking fees management system in areas.On the basis of other people's research, this paper has researched and designed LPR associating with wavelet analysis. This paper has mainly the following three parts: first, extracting the license plate, the paper use wavelet analysis's characteristics of multi-resolution to decomposite and reconstructe the information of the license plate region, so that it can highlight license region. The image of license plate is binarized using local threshold method. and the lineation of the license plate is highlighted used mathematical morphology of open of the operation. the line and the array of the lineation of the license plate are projected. Secondly, splitting the characters, It combine with LapLace algorithm for edge detection, Then the license plate characters are separated from the top convex features of characters to the bottom convex features of characters. Third, recognizing the character, the method combined with the lineament of the character and neural network recognize the character of the license plate.The results of simulation show that the system can accurately locate the license plate and recognize characters and system's performance is good. It shows that wavelet analysis and recognition techniques can improve the ability of recognition. Under the principle of efficiency and practicality ,neural network and artificial intelligence will be one major development tendence of parrern recognition.