The rupiah is a legal tender used in transactions in the Republic of Indonesia and
ratified by Law No. 23, 1999. The counterfeit money in the transaction is very
inhibiting in economic activities such as: transactions, lending and exchange.
Rupiah often counterfeited namely in the form of paper currency. The design of
the authenticity of the identification system rupiah using the K-NN method aims to
make it easier to identify the authenticity of currency and test the level of
accuracy of the method used. The method used in this research is the method of
Gray Level Coocurence Matrix (GLCM) as feature extraction method and the
method of K-Nearest Neighbor (K-NN) is used in the process of classification and
identification. The testing phase uses the data as many as 18 images currencies.
The results showed 100% accuracy rate for the value of k = 1, 77.78% to the
value of k = 3, and 55.56% to the value of k = 5. The highest accuracy rate in
identifying the authenticity of the currency system occurs when the value of k = 1
is 100%.