Abstract: According to the problem of decreased recognition rate by the degradation of the banknote image,a real time banknote image classification method based on hidden markov models is presented in this paper.Firstly,the proposed method is used to preprocess the banknote image,and then wavelet transform is applied to extract the texture characteristics of banknote.At last,hidden markov model is used to classify the banknote image.In order to verify the validity of the proposed method,the experiments are conducted on different banknotes.The experimental results show that the proposed method overcomes the influence of banknote image degradation on the recognition rate and obtains high recognition rate and high stability.