Monday, May 4, 2009

Google’s Book scanning machine

This Patent application by Google describes a method to automatically scan books while correcting for the curvature of the binding so that it is easier for the OCR software to convert it into text. That sound you hear? the desperate cries of a thousand book publishers. [Link, Link]

What is claimed:
1. A system comprising: an infrared projector; a pattern mask located in an output path of the infrared projector; a stereoscopic camera to generate images of opposing pages of a document from which a three-dimensional image of a surface of the opposing pages of the document is generated; and control logic to process the three-dimensional image to locate a groove that is defined by the spine of the document and located between the opposing pages of the document.

No comments:

Post a Comment