Notes Sorting And Anti-counterfeit Technology Research Based On The Light And Electrical Signal

With the rapid growth of China's economy,the cash in circulation grows so fast and people tend to have high demands on the quality of banknotes,which result in the arise of Class-A bill counter, sorter, ATM machines and other financial equipments that have sorting and distribution capacity.Currency Sorter mainly classifies the new and used bills, face direction, denomination and authenticity of the bills, thus inhibiting the circulation of damaged paper and counterfeit money.Most financial institutions are currently screening bills by manual operations, which can be labor-intensive and time-lasting, and the sorting results are not so satisfying. As the study of the bill sorting has just started in our country, there are just a few trustworthy counterfeiting and sorting machines. Coupled with the growing counterfeit manufacturing technology, the research of banknotes sorting is so important that it is related to the country's financial security and has great theoretical significance and broad prospects for use.In this paper,we mainly studied banknotes counterfeiting and sorting technology based on optoelectronic signal. Among them,the optical signals mainly consist of purple light, fluorescent light, infrared light and ultra violet, and electrical signals mainly consist of weak magnetic signal and thickness signal.This paper came up with a banknotes counterfeiting and sorting scheme based on optoelectronic signal.The use of encoder signal and CD4051 time division multiplexing can help collect several valid signals accurately.By analyzing the original banknote signals and the characteristics of noise, this paper designed a software-based signal denoising algorithm. Aiming at the overload of information, this paper put forward a PCA-based feature extraction method. On account of the division of some similar and unstable signals, a singular feature extraction method bases on wavelet was proposed. In order to improve the accuracy of sorting, this paper presented a SVM classification method by overall considering all the features.This method can not only identify the orientation of RMB accurately, it can also be applied to other currencies.The proposed banknote counterfeiting and sorting method based on optoelectronic signals was examined and tested on certain platform with RMB. Compared with traditional methods,it has faster processing speed, less amount of collected data and more information.What's more, it has a good adaptability for different types of banknote images, and a higher recognition rate of banknote orientation. The schemes and algorithms described in this paper have been achieved commercial production, and applied in a number of large banks.