Method for identifying authenticity of banknote based on banknote anti-counterfeiting point multiple-feature fusion

Abstract

The invention provides a method for identifying the authenticity of a banknote based on banknote anti-counterfeiting point multiple-feature fusion. The method comprises the following steps: the same weak classifier is trained by an AdaBoost algorithm for different training sample sets; the weights of the training samples and the weak classifier are adjusted according to wrongly-classified training samples in the training sample sets and the situation of training sample wrong classification in the weak classifier; the weak classifier is retrained after the training sample sets are redistributed; the above steps are repeated, and T weak classifiers and the weight corresponding to each weak classifier are obtained after the weak classifier is trained T times; the T weak classifiers are integrated into a final strong classifier; and the trained strong classifier tests a test sample set, statistical analysis is made on the test error rate, and the steps are repeated until the steps are repeated a set maximum number of times T and a classification model based on fusion of anti-counterfeiting points of the sample sets is obtained.

Description

technical field [0001] The invention relates to the technical field of banknote identification, in particular to a method for identifying the authenticity of banknotes based on the multi-feature fusion of banknote anti-counterfeiting points based on the AdaBoost algorithm. Background technique [0002] With the prosperity and development of the economy, the circulation of banknotes is increasing. Various versions of counterfeit money produced by some criminals emerge in an endless stream, endangering the financial security of the country. At present, the core technology of the multi-spectrum banknote counters, sorting machines, and deposit and withdrawal machines used by our country's banks comes from abroad, which is not only expensive, but also unable to recognize some counterfeit currency. [0003] The principle of counterfeit identification of multi-spectral banknote counters, sorting machines, cash machines and other machines commonly used in China is: real-time bankno...

AI Technical Summary

Problems solved by technology

Due to the unavoidable image shift and the limited identification features, the identification stability and identification ability cannot meet the requirements of people's expectations for identifying the authenticity of banknotes.

[0004] The application number 20110088920.X published in the Chinese patent literature is "a banknote authentication method and device", which uses a collection device to obtain the transmission image of the area where the window-type security line indentation feature on the banknote is transmitted by the light beam, and analyzes and identifies the transmission image. Figure the indentation features in the lower layer to judge the authenticity of banknotes. Although the patent can identify the authenticity of banknotes to a certain extent, this method belongs to local feature identification.

[0005] The Chinese patent literature published application number 201310027700.5 is "a method for identifying counterfeit RMB based on the image features of the serial number", which mainly identifies the authenticity based on the color and font size of the serial number. This method has a low recognition rate and cannot recognize spliced ​​coins whose right half is fake

[0006] It can be seen that the main technical difficulties in banknote authentication at present are: high recognition speed requirements, difficult to extract image features, and various spectral images of counterfeit banknotes. Rodness, to ensure the robustness of the system, to ensure the safety of the system in abnormal and dangerous situations

Images