Compression Algorithms In Some Photocopiers Are Changing Numbers On Scanned Documents

6 August 2013

David Kriesel:

In this article I present in which way scanners / copiers of the Xerox WorkCentre Line randomly alter written numbers in pages that are scanned. This is not an OCR problem (as we switched off OCR on purpose), it is a lot worse – patches of the pixel data are randomly replaced in a very subtle and dangerous way: The scanned images look correct at first glance, even though numbers may actually be incorrect.

Until now, I’ve taken it for granted that the photocopier produces a direct copy of your image, subject only to the resolution of the scanner and limitations in print quality. The idea of a photocopier being ‘smart’ and perform post-processing on the scanned image had not crossed my mind.

The crazy thing is, these errors could have very serious ramifications.