Reseach on the Paper Currency Recognition Based on Neural Network Algorithm
Peng Jun-min · Journal of Xi'an University of Technology · 2008
The priority given to research on paper currency recognition lies in the accuracy and velocity of recognition.In this paper,the authors adopt the feed-forward neural network with a comparatively easy structure,select the suitable paper currency sampling features to be the network inputting characteristics,and use Scaled Conjugate Gradient(SCG) algorithm to conduct the rapid and efficient training for the network,whereby the swift and accurate recognition of paper currency can be realized.The result of the experiment demonstrates that the proposal is feasible and effective.