Digitizing Books One Word at a Time.

Now that I've written about CAPTCHA (read it here), let me tell you something about reCAPTCHA.

reCAPTCHA is a free CAPTCHA service that helps to digitize books. Millions of CAPTCHAs are solved by humans around the world every day. In each case, roughly ten seconds of human time are being spent. reCAPTCHA channels the effort spent solving CAPTCHAs online into "reading" books.

Using Optical Character Recognition, the photographically scanned book pages are transformed into text. The problem is that OCR is not perfect.

reCAPTCHA improves the process of digitizing books by sending words that cannot be read by computers to the Web in the form of CAPTCHAs for humans to decipher. More specifically, each word that cannot be read correctly by OCR is placed on an image and used as a CAPTCHA. 

Here is the tricky part. If a computer can't read such a CAPTCHA, how does the system know the correct answer to the puzzle? Here’s how: They give two words instead of one – one which cannot be read correctly by OCR and the next word for which the answer is already known. The user is then asked to read both words. If they solve the one for which the answer is known, the system assumes their answer is correct for the new one. 

What if we can read only one of them? Say, something like this.

I enter the word ‘(Humphrey’ correctly but not the next. In this case, it will be still considered correct but it would not take it for granted. The system then gives the new image to a number of other people to determine, with higher confidence, whether the original answer was correct.

Ref: reCAPTCHA / WIKI