Counterfeit detection using paper PUF and mobile cameras

This work studies the paper authentication problem by exploiting optical features through mobile imaging devices to characterize the unique, physically unclonable properties of paper surface. Prior work showing high matching accuracy either used a consumer-level scanner for estimating a projected normal vector field of the surface of the paper as the feature for authentication, or used an industrial camera with controlled lighting to obtain an appearance image of the surface as the feature. In comparison, past explorations based on mobile cameras were very limited and have not had substantial success in obtaining consistent appearance images due to the uncontrolled nature of the ambient light. We show in this work that images captured by mobile cameras can be directly used for authentication by exploiting the camera flashlight to create a semi-controlled lighting condition. We have proposed new algorithms to demonstrate that the microscopic normal vector field of paper surface can be estimated by using multiple camera-captured images of different viewpoints. Our findings can relax the restricted imaging setups to enable paper authentication under a more casual, ubiquitous setting of a mobile imaging device, which may facilitate duplicate detection of paper documents and merchandise packaging.