reCaptcha
- Started
- Last post
- 12 Responses
- jimbojones
I don't get how it works, they say by entering the words we help digitizing books, they give us words their OCR couldn't process. But how do they know if the word is entered correctly if the OCR can't confirm it?
- heavyt0
i would guess it is a matter of aggregating the response from many users. Whatever the most common answer is, probably is correct. I ma guessing though, since I have no idea what you are talking about.
- PonyBoy0
what?... where's the porn, jim?
- prophet0NE0
i ask myself this all the time. how do they validate it if the purpose is to know what it is in the first place? it must be voodoo economics.
- drgss0
they always give you two words for verification, one is processed (!) the other one is not
- how can they verify the unprocessed one?jimbojones
- it's notscarabin
- scarabin0
one is made up and is the one actually used by the captcha.
the second one is a word from an old newspaper or book that their OCR software can't identify. when you identify the word it's compared to other people's answers and if enough people identify it as the same word it's used by the OCR app
- jimbojones0
Each new word that cannot be read correctly by OCR is given to a user in conjunction with another 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. The system then gives the new image to a number of other people to determine, with higher confidence, whether the original answer was correct.
- kulor0
I think that's really bloody clever.
- bklyndroobeki0
http://www.shieldsquare.com/blog…
what do you use?
- uan0
track mouseevents...bots don't use them.