A pretty cool project was brought to my attention today by a co-worker as well as digg. The project is reCAPTCHA, a project from Carnegie Mellon University, and Luis von Ahn, one of the pioneer CAPTCHA developers. reCAPTCHA aims at “recycling” human brain power used when we are forced to enter CAPTCHA text on websites. reCAPTCHA does this by providing website developers with a library, which instead of presenting a random piece of text to the user for processing, uses previously scanned pieces of text from books being digitized. reCAPTCHA creates CAPTCHA images from text the OCR system was unable to identify successfully, essentially leaving the recognizing to the experts, us humans. As a result, CAPTCHA’s ability is extended to aiding in the accurate digitalization of books, ultimately killing two bird with one stone. Brilliant stuff.

2 thoughts on “reCAPTCHA

Leave a Reply

Your email address will not be published.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

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>