License Plate Recognition (LPR) system is a key to many traffic related applications such as road traffic monitoring or parking lots access control. This paper proposes an automatic license plate recognition system for Jordanian license plates. The system presents an algorithm for the detection of license plate and segmentation of characters, and then recognition is done using back propagation neural network. The gain contribution of this work is the improvement of the license plate detection subsystem, which in turn improves the whole LPR system. The performance of the proposed system has been investigated on real images of 240 vehicles captured under various illumination conditions. The results show a robust algorithm with average success rate of 90% for Jordanian license plates.