Google Data API has included an amazing new feature and that is OCR (Optical Character Recognition). Google has recently launched it as part of API. Currently as an experimental feature but its amazing!!

Google OCR create Google Document from an image containing text. A high resolution image is though needed for the OCR to work perfectly. The quality of the extraction is not yet up to the perfect standard but its quickness is really one hell of a gem. Currently only JPG, GIF and PNG types are supported. Other conditions are

• Files must be fairly high-resolution -- rule of thumb is 10 pixel character height.
• Maximum file size: 10MB, maximum resolution: 25 mega pixel
• The larger the file, the longer the OCR operation will take (500K: ~15s, 2MB: ~40s, 10MB: forever)

You need to have Google Docs account to make the OCR work.  Go ahead and catch the live demo here

Note: Try google image search to find high resolution image. If you can't find one, try this one , SAMPLE IMAGE