Research on Algorithm for Automatic License Plate Recognition System

License plate recognition belongs to the field of computer vision and pattern recognition, and plays an important role in the field of intelligent transportation. The license plate location is a key technology in license plate recognition, the accurate positioning of a license or not directly affects the accuracy of character segmentation and character recognition, and has a direct impact on the efficiency of the license plate recognition system. In this paper, based on knowledge acquisition and knowledge reduction ability of rough set, as well as learning ability and generalization ability of neural network, a plate positioning system is constructed. On this basis, combined the rough set with neural networks and fuzzy logic, a rough fuzzy neural network recognition is proposed. The experimental results show that this system not only simplifies the structure of the system, but also improves the generalization capability of knowledge, and improves the accuracy of character positioning.