Abstract.
A method for detecting full layout facsimile duplicates based on radial pixel densities is proposed. It caters for facsimiles, including text and/or graphics. Pages may be positioned upright or inverted on the scanner bed. The method is not dependent on the computation of text skew or text orientation. Using a database of original documents, 92% of non-duplicates and upright duplicates as well as 89% of inverted duplicates could be correctly identified. The method is vulnerable to double scanning. This occurs when documents are copied using a photocopier and the copies are subsequently transmitted using a facsimile machine.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
Received September 29, 2000 / Revised: August 23, 2001
Rights and permissions
About this article
Cite this article
Chatelain, P. Identifying facsimile duplicates using radial pixel densities. IJDAR 4, 219–225 (2002). https://doi.org/10.1007/s100320100065
Issue Date:
DOI: https://doi.org/10.1007/s100320100065