Distortion Measurement for Automatic Document Verification

Document forgery detection is important as techniques to generate forgeries are becoming widely available and easy to use even for untrained persons. In this work, two types of forgeries are considered: forgeries generated by re-engineering a document and forgeries that are generated using scanning and printing a genuine document. An unsupervised approach is presented to automatically detect forged documents of these types by detecting the geometric distortions introduced during the forgery process. Using the matching quality between all pairs of documents, outlier detection is performed on the summed matching quality to identify the tampered document. Quantitative evaluation is done on two public data sets, reporting a true positive rate from to 0.7 to 1.0.

I Introduction

Document forgery is a common problem affecting many areas of everyday commercial activities. One prominent example is that of insurance companies: due to advances in document digitization and information extraction, incoming invoices are digitized and information is automatically extracted. The further processing is solely done on the digital data and thus, even plumply tampered documents may lead to a successful defrauding of money. Automatic tools for identifying tampered documents are thus needed.