We’ve all seen CAPTCHA before on the net, those little distorted words used to confirm that we’re in fact human. reCAPTCHA takes this idea and adds the usefulness by making everyone read old books one word at a time. Intrigued? Here’s why it’s being done and how it works:
In order for the internet to truly be the “information superhighway” several projects are currently actively digitizing text written before the digital age. Pages of text are scanned into the computer and a computer program using “Optical Character Recognition” (OCR) figures out what the letters are. The problem with OCR is that computers can’t read text as well as humans can, so the resulting words are typo-prone.
reCAPTCHA makes humans do the work that only humans can do, read distorted but readable text. Instead of just a random arbitrary distorted word to confirm we’re human, we are given a word that computers can’t read and one word that some other human have already read. Each reCAPTCHA we do helps take another step to fully digitizing these books. You can find more information on the reCAPTCHA home page.