ARCHIVE / What is reCAPTCHA?

reCAPTCHA is a project centered out of Carnegie Mellon University that generates CAPTCHAs that are used to digitize books.  While this may seem odd or simply an act of charity, it is in fact a brilliant means of providing and receiving valuable services.  The principle behind reCAPTCHA is that when books are digitized, not all of the words being scanned by an optical scanner can be converted to text due to imperfections with the typesetting, damage to the page or other markings.  These problematic segments are precisely the ones that human beings find easy to distinguish while computers have difficulty converting to text and are thus an excellent basis for a CAPTCHA.  Likewise, the generally non-profit projects that are digitizing these old books need people to perform the tedious task of identifying and typing in the problematic segments.  By requiring that human beings type in two words for two different problematic segments, reCAPTCHA can provide one known word as a CAPTCHA and the other as a means of determining a piece of problematic text and thus digitizing a book.

RELATED PAGES

RELATED TOPICS