Running text-conversion on PDF files

Evernote runs text-recognition on all the images uploaded to their service. This great feature allows you to search through photos taken of notes and printouts. How does Evernote do it? It sounds like a fairy land.

I’m using Adobe Acrobat Pro to OCR a batch of 32 PDF files that I scanned on the printer at 300 dpi. It takes a good amount of time for it to process each PDF. 388 pages in 32 PDF files took 37 minutes running on a 2011 Macbook Pro (Intel Core i7 Processor 2GHz with 4GB SDRAM RAM).

That’s 10.4 pages per minute. (6.5 seconds per page)

I don’t know how Evernote manages to do text recognition in all those photos uploaded to the service. Kudos to Evernote for providing this service and all the processor power it requires.

Do you use the text recognition feature in Evernote? If so, let me know your thoughts about the service in the comments. Thanks!