Do you see what I see?
Deciphering digitized text can be a laborious process of reading the text word for word and checking the OCR results against a paper copy. A recent BBC.com article highlighted the efforts of Luis von Ahn and his novel solution to translating texts. Using the CAPTCHA technology, or more specifically reCAPTCHA, von Ahn lets the user’s process of validating visual security codes translate the slightly obscured text. We all have seen something similar when we type in random characters in order to access secure web sites. This application of those measures serves the needs of the libraries without impacting those who have been unknowingly drafted for this task.
The texts are being taken from the Internet Archive which features thousands of books from which to choose from. Not only is the project helping to fight spam but it is also helping to preserve pieces of our shared cultural history.
Luis von Ahn stated in the aforementioned article, “There’s still about 100 million books to be digitised, which at the current rate will take us about 400 years to complete.” Let’s hope innovations such as this will make that span of time become something we can all marvel at within our life spans.