Testing Google’s OCR

Previously, I briefly mentioned the optical character recognition (OCR) technology within Google Docs. I decided to test it in the relatively challenging circumstance of converting photographs of pages from a book into text:

As you can see, the image to text conversion isn’t perfect. Indeed, it doesn’t work terribly well in the conditions to which I subjected it. Substantial strings of text are missing, and there are many errors.

Probably, the system would work better if the pages had been perfectly flat and evenly illuminated, and if my camera had been perfectly parallel to the page.

Author: Milan

In the spring of 2005, I graduated from the University of British Columbia with a degree in International Relations and a general focus in the area of environmental politics. In the fall of 2005, I began reading for an M.Phil in IR at Wadham College, Oxford. Outside school, I am very interested in photography, writing, and the outdoors. I am writing this blog to keep in touch with friends and family around the world, provide a more personal view of graduate student life in Oxford, and pass on some lessons I've learned here.

One thought on “Testing Google’s OCR”

  1. I am surprised it works so poorly. How did they get so much into Google Books?

Leave a Reply

Your email address will not be published. Required fields are marked *