Wednesday, April 22, 2009

Optical Character Reading (OCR)

I have a rather large document that I wanted to send to a North Island colleague. As it is many years old, and I had no electronic version of it, I had to photocopy and post. Unfortunately, the envelope has vanished into the bowels of NZ Post, and is yet to emerge nearly two weeks later. With a deadline rapidly approaching, my solution was to turn to Optical Character Reading, which turns a scan of a page into editable text. I found a freeware OCR progam at simpleocr.com, and while it doesn't have all the bells and whistles of some of the more sophisticated paid programs, it has done the job fine, with a high accuracy rate on the text conversion. It's biggest deficiency was being unable to handle tables or multiple columns, but as there were few of those in my document, it was no big deal to just retype them.

No comments: