In the last decades, the number of vehicles has increased drastically. With this increase, it is becoming difficult to keep track of each vehicle for the purpose of law enforcement and traffic management. Automatic License Plate Recognition is implemented to make human work easier besides it can reduce the uses of human power because of its flexibility and the easy of its implementation. In this paper we propose an efficient algorithm for automatic recognition of any license plate, with an emphasis on the Lebanese license plates where some of their features have been exploited well to reduce the recognition errors. The proposed algorithm has been implemented using the Image Processing Toolbox in MATLAB R2013b (8.2.0.701). Our simulations show that the recognition errors have been reduced well upon exploiting the fact that the Lebanese license plates are written in two formats (Arabic and Hindi). Furthermore, our algorithm has an option to benefit from the presence of the license plates in the front and the rear end of the car to enhance the performance.