License plate recognition is an important part of intelligent transportation systems, and image feature extraction and recognition are the key processes. This paper describes a method of license plate identification. Firstly, wavelet transform modulus maxima is used to detect edges for the segmented characters of the plate, then the features of relative moment are extracted. Secondly, the features are fed into BP neural network for classification. Experiment results show that the method is efficient and has good recognition rate.
展开▼