SECURE IDENTIFICATION DOCUMENTS VIA PATTERN-RECOGNITION AND PUBLIC-KEY CRYPTOGRAPHY

Personal identification documents, such as photo ID cards, are being u sed increasingly for such activities as financial transactions; entry into restricted areas; and personal verification for medical, governme nt, and commercial (in particular, airlines) services. With this trend , there is also the increasing trend toward counterfeiting these docum ents for illegal gain. We present an approach to authenticating photo- ID documents that relies on pattern recognition and public-key cryptog raphy and has security advantages over physical mechanisms that curren tly safeguard cards, such as optical laminates and holograms. The patt ern-recognition component of this approach is based on a photo signatu re that is a concise representation of the photo image on the document . This photo signature is stored in a database for remote authenticati on or in encrypted form on the card for stand-alone authentication. Ve rification of the ID document entails scanning both the photo image an d a machine-readable form of the text information, determining the pho to signature, and comparing this information against the reference. In this paper, we describe the method and present results of testing a l arge database of images for photo-signature match in the presence of n oise.