I greatly admire the reCaptcha project including the less popular reCaptcha Mailhide. reCaptcha is really clever as, whilst on the one hand providing verification for Website content, on the other and at the same time digitized content that optical character recognition (OCR) software can’t decifer is solved by humans. reCaptcha provides a great service to character recognition for the digitizing of documentation (and hence making knowledge more freely available and widespread).
… reCAPTCHA gives the user two words, the one for which the answer is notknown and a second “control” word for which the answer is known. If users correctly type the control word, the system assumes they are human and gains confidence that they also typed the other word correctly … (Science Magazine)
I did however get totally ‘stumped’ by a Captcha I came across recently. Per the image of the Captcha, the characters were both in English and Hebrew. There was quite simple no way that I was going to successfully enter both terms correctly so refreshed the Captcha.
Google now runs reCaptcha and are using it with their massive text digitization projects. Keep up the great work Google!
Leave a Reply