Friday, October 31, 2008

Google can read text from images

Google has recently announced in their official blog that they are now using Optical Character Recognition (OCR) technology to index and show an HTML version of a scanned PDF document.

In the past, Google only showed an HTML version of PDF's created with text enabled formatting. But from now, if a document is scanned as an image, Google can also read it and create an HTML version for it (click “View As HTML” in the search results).

Click on these following search queries to see how it works (given by Google itself in their official blog) -
[repairing aluminum wiring]
[spin lock performance]
[Mumps and Severe Neutropenia]
[Steady success in a volatile world]

No comments:

Post a Comment