If you're not a developer, you're probably not aware that Google Docs has an API available for various document-related services. Recently Google added a new feature that allows developers to create applications that will pass an image-based (.png, .jpg, or .gif) document to the API, and using OCR (Optical Character Recognition) technology, generate and pass back an editable text-based document. Currently the service can handle documents up to 10 MB in size.

For non-developers, this is certainly interesting, but not terribly useful. Well, a live demo is available that will allow you to test the service yourself. At the time of this writing I was successfully able to convert a single page document, though there are reports that the service has become overloaded and is slow or sometimes fails to respond. Given that this is a demo, that's probably not terribly surprising.

If Google is exposing this functionality to developers, it seems at least possible that it could become a built-in feature of Google Docs for regular users at some point in the near future. With Google's recent acquisition of reCaptcha, it seems likely that Google's document-scanning capabilities will soon be better than anyone else's. That would make for an incredibly powerful feature for Google to offer its users.

[via Google Operating System]