An automatic method of location for number-plate using color features

This paper presents an automatic method of location for a number-plate using color features. In this method, the pixel colors of the number-plate area are classified using a neural network, then color features are extracted by analyzing scanning lines of the cross-section of the number-plate. It makes full use of the number-plate color features to locate the number-plate. The experimental results show that the correct rate of number-plate location is close to 100%, and the time of number-plate location is less than 1 second. It is also observed that this system is not sensitive to variations of weather, illumination and vehicle speed. In addition, and also it does not require the size of the number-plate to be known in prior. This system is of crucial significance is to apply and spread the automatic system of vehicle plate recognition.