Tagged: ocr Toggle Comment Threads | Keyboard Shortcuts

  • raj 6:50 pm on April 26, 2011 Permalink | Reply
    Tags: ocr, recaptcha   

    The OCR capacity of recaptcha 

    From Prof. von Ahn:

    …about 100 million words/day, or the equivalent of 2.5 million books/year

    via this TEDxCMU talk about Luis von Ahn’s new company, duolingo:

     
  • raj 10:22 pm on March 25, 2011 Permalink | Reply
    Tags: newspapers, ocr   

    Help correct OCR in Finnish newspapers by playing games 

    Via Peter:

    Digitalkoot is a joint project run by theĀ National Library of Finland andĀ Microtask. Our goal is to index the library’s enormous archives so that they are searchable on the Internet. This will enable everyone to easily access our cultural heritage.

    You can help us by playing games.

    Playing games in Digitalkoot fixes mistakes in our index of old Finnish newspapers. This greatly increases the accuracy of text-based searches of the newspaper archives.

     
c
Compose new post
j
Next post/Next comment
k
Previous post/Previous comment
r
Reply
e
Edit
o
Show/Hide comments
t
Go to top
l
Go to login
h
Show/Hide help
shift + esc
Cancel