A hybrid technique for License Plate Recognition based on feature selection of wavelet transform and artificial neural network

A number of vehicles may be controlled and supervised by traffic security and its management. The License Plate Recognition is broadly employed in traffic management to recognize a vehicle whose owner has despoiled traffic laws or to find stolen vehicles. Vehicle License Plate Detection and Recognition is a key technique in most of the traffic related applications such as searching of stolen vehicles, road traffic monitoring, airport gate monitoring, speed monitoring and automatic parking lots access control. It is simply the ability of automatically extract and recognition of the vehicle license number plate´s character from a captured image. Number Plate Recognition method suffered from problem of feature selection process. The current method of number plate recognition system only focus on local, global and Neural Network process of Feature Extraction and process for detection. The Optimized Feature Selection process improves the detection ratio of number plate recognition. In this paper, it is proposed a new methodology for `License Plate Recognition´ based on wavelet transform function. This proposed methodology compare with Correlation based method for detection of number plate. Empirical result shows that better performance in comparison of correlation based technique for number plate recognition. Here, it is modified the Matching Technique for numberplate recognition by using Multi-Class RBF Neural Network Optimization.