Research on identification the counterfeit by recognizing the infrared images

Paper currency identification is widely applied in many fields such as bank system and automatic selling-goods system. How to extract high-qualified monetary characteristic from currency images is an important technology needing to be solved now. Infrared images can reveal the Intaglio Printing of paper currency, which extent the traditional touching the concavo-convex effect to use images to identify the counterfeit. The contrast of infrared images is not great. It is influenced by uneven surface and other disturbances (such as fold, holes etc.), so using traditional processing and enhancement technologies are hard to identify the counterfeit. In this paper, the original infrared images have been embossed process firstly. Then we gain the binary images by using closing operation. At last, we use template matching to identify. Using this method can get very good experiment result ant the recognition rate is 100% in the application.