Slashdot Mirror

I did that protect your email address with OCR thing at http://mailhide.recaptcha.net/ and tried solving it myself. I mistyped one of the words accidentally and noticed a second after I hit enter. It said 'Congrats you're a human!' and proceeded to give me the address.

You can try it out at the top of this page.

Here's the website, http://recaptcha.net/

I came across this but haven't tried it yet: http://www.bad-behavior.ioerror.us/ and of course, there are other interesting ways to prevent submissions: http://recaptcha.net/learnmore.html

If your web site uses captcha, you get spam from posting your email address online, or you just want to help out the Internet Archive's book project, check out recaptcha. It's a captcha based around helping recognize difficult-to-OCR scans.

-snarkbot

I switched to recaptcha, which uses OCR'ed texts to validate. Ever since I switched I don't get the automated spammers signing up. There are plugins for various languages and bulletin board sytsems (such as phpbb). It has a side-benefit of correcting OCRed public domain books.

Reminds me of that somewhat bizarre subplot in Vinge's latest novel "Rainbow's End" where there was a big project to digitize all the university libraries, and some guy came up with the fastest way to do it: just throw all the books into a giant shredder, and then gave lots of cameras taking pictures of every last bit from every andle as it comes blowing out the other end...then re-assemble it all in a computer.

http://recaptcha.net/

There needs to be a I don't know button as well :)

From the security page of the reCAPTCHA site: "if somebody writes a program that can read our distorted images, we can add more distortions in very little time"

If someone can write a program to solve the distorted images of OCR-unreadable words, don't you just hire that guy to do your OCR and get out of the CAPTCHA business?

http://recaptcha.net/security.html the words are additionally distorted and they add lines and warps so that a computer cannot read it.

"But if a computer can't read such a CAPTCHA, how does the system know the correct answer to the puzzle? Here's how: 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."

http://recaptcha.net/learnmore.html

"But if a computer can't read such a CAPTCHA, how does the system know the correct answer to the puzzle? Here's how: 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."

I originally missed the link to the official site - D'oh. The article also doesn't mention that the system is already in use! http://recaptcha.net/

The article is lacking some information. Here are some better links:

Official reCAPTCHA site
Hide your email address with reCAPTCHA (super easy!)
A more detailed blog post about how the system works

Disclaimer: I work with Luis von Ahn, who's the professor running the reCAPTCHA project.

The article is lacking some information. Here are some better links:

Official reCAPTCHA site
Hide your email address with reCAPTCHA (super easy!)
A more detailed blog post about how the system works

Disclaimer: I work with Luis von Ahn, who's the professor running the reCAPTCHA project.

From recaptcha.net: "But if a computer can't read such a CAPTCHA, how does the system know the correct answer to the puzzle? Here's how: 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."