...a patent awarded to Google gives insight into how the search behemoth accomplishes the task.Of course, this is just a piece of the technology that Google is using. Maybe future patents will reveal more?In short, Google has come up with a system that uses two cameras and infrared light to automatically correct for the curvature of pages in a book. By constructing a 3D model of each page and then "de-warping" it afterward, Google can present flat-looking pages online without having to slice books up or mash them onto a flatbed scanner.
BTW information flows on the Internet in many different ways these days. The way I found out about this was through a Facebook status update by SivaVaidhyanathan.
Technorati tags:
Digitization, 
Google, 
Book
3 comments:
Not necessarily.. it was also prominently featured on engadget..
Anonymous...I'm sure that this news was featured in many places, but I was highlighting where I tripped over it. We may come across interesting news in many ways...more so now than ever.
The excitement about any hint relevant to Google in-house activities obfuscates a reasonable assessment of the state of the art for bookscanning:
CNet's article only considers sheet-fed scanners, which require to guillotine the books, and common flat-bed face-down scanners.
Two other technologies are available:
Some facedown flatbed scanners (Plustek's for instance) avoid "mashing" the binding without requiring to open books at 180°.
Face-up book scanners (Zeutschel, Kirtas, i2S, for instance) with book cradles protect bindings, facilitate handling, correct images. Kirtas is using two cameras...
The innovation (?) in the patent should be looked for in the stereo infrared captor.
Face-up (industrial) bookscanners (and OCR packages) have been using for quite a while different solutions to deskew lines near the spine.
More information is needed before talking of a "competitive advantage".
Disclaimer: I am working for i2S, one of the main industrial bookscanners manufacturers
Post a Comment