reCAPTCHA: Human-Based Character Recognition via Web Security Measures | Zendy

Luis von Ahn | Zendy; Benjamin Maurer | Zendy; Colin McMillen | Zendy; David Abraham | Zendy; Manuel Blum | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Open Access

reCAPTCHA: Human-Based Character Recognition via Web Security Measures

Author(s) -

Luis von Ahn,

Benjamin Maurer,

Colin McMillen,

David Abraham,

Manuel Blum

Publication year - 2008

Publication title -

science

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 12.556

H-Index - 1186

eISSN - 1095-9203

pISSN - 0036-8075

DOI - 10.1126/science.1160379

Subject(s) - captcha , decipher , computer science , character (mathematics) , turing test , task (project management) , world wide web , optical character recognition , matching (statistics) , word (group theory) , turing , test (biology) , web application , information retrieval , natural language processing , artificial intelligence , linguistics , image (mathematics) , bioinformatics , engineering , paleontology , statistics , philosophy , geometry , mathematics , systems engineering , biology , programming language

CAPTCHAs (Completely Automated Public Turing test to tell Computers and Humans Apart) are widespread security measures on the World Wide Web that prevent automated programs from abusing online services. They do so by asking humans to perform a task that computers cannot yet perform, such as deciphering distorted characters. Our research explored whether such human effort can be channeled into a useful purpose: helping to digitize old printed material by asking users to decipher scanned words from books that computerized optical character recognition failed to recognize. We showed that this method can transcribe text with a word accuracy exceeding 99%, matching the guarantee of professional human transcribers. Our apparatus is deployed in more than 40,000 Web sites and has transcribed over 440 million words.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.

Having issues? You can contact us here

Accelerating Research