Principal Component Analysis of Diffuse Near-Infrared Reflectance Data from Paper Currency

Abstract

Product tampering and product counterfeiting are increasing the need for methods to quickly determine product authenticity. One of the concepts that we are investigating for the detection of counterfeit objects involves the use of pattern recognition techniques to analyze multivariant data acquired from properties intrinsic to the object. The near-infrared reflectance spectra of currency and other paper stock were used as a test system. The sample population consisted of authentic currency, circulated and uncirculated, and cotton and rag paper stock as stand-ins for counterfeit currency. Reflectance spectra were obtained from a spot that was essentially void of printing on both sides of the currency specimens. Although the reflectance spectra for all of the samples were very similar, principal component analysis separated the samples into distinct classes without there being any prior knowledge of their chemical or physical properties. Class separation was achieved even for currency bills that differed only in their past environment. Leave-One-Out procedures resulted in 100% correct classification of each member of the sample set. A K-Nearest-Neighbor test or a linear discriminate can be used to correctly classify unknown samples.