Paper Currency Recognition Based on Feature Extraction of One Dimension Fourier Transform
Yin Hui-ling · Computer and Modernization · 2011
A system of paper currency recognition includes image collection,preprocessing,feature extraction and classifier design.A critical step is the feature extraction which directly influences the recognition effect of the whole system.Especially to recognize paper currency which are different in par value but similar in length,width and pattern,a new feature extraction method is proposed,which is based on one dimension Fourier transform in part area.The experiment result shows that this method leads to a high recognition rate and is of excellent value in practical application.