OPTICAL RECOGNITION OF MOTOR-VEHICLE LICENSE PLATES

In this paper a system for the recognition of car license plates is pr esented. The aim of the system is to read automatically the Italian li cense number of a car passing through a tollgate. A TV camera and a fr ame grabber card are used to acquire a rearview image of the vehicle. The recognition process consists of three main phases. First, a segmen tation phase locates the license plate within the image. Then, a proce dure based upon feature projection estimates some image parameters nee ded to normalize the license plate characters. Finally, the character recognizer extracts some feature points and uses template matching ope rators to get a robust solution under multiple acquisition conditions. A test has been done on more than three thousand real images acquired under different weather and illumination conditions, thus obtaining a recognition rate close to 91%.