Google Book Search: Document Understanding on a Massive Scale

Unveiled in late 2004, Google Book Search is an ambitious program to make all the world's books discoverable online. The sheer scale of the problem brings a number of unique document analysis and understanding challenges that are outlined in this paper. We also go over some of the ways that Google is working with the document analysis research community to help push the state of the art. Google Book Search started as a dream: the dream by Google co-founders Larry Page and Sergey Brin that one day, all the world's books might be discoverable online, through a kind of electronic and distributed Library of Alexandria. Today, thanks to advances in scanning and storage technology, to significant investment by Google and to a lot of hard work by a lot of dedicated Googlers and partners, this dream is well on its way to becoming a reality. Google Book Search, originally named Google Print, was launched in late 2004. Over a million books have been scanned to date and Google Book Sea...

• Type: Conference
• Year: 2007
• Where: ICDAR
• Authors: L. Vincent
• Keywords: Books, Document Analysis, Google Book Search, ICDAR 2007, World's Books