Title :
Google Book Search: Document Understanding on a Massive Scale
Author_Institution :
Google, Mountain View
Abstract :
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.
Keywords :
document handling; literature; search engines; Google Book Search; document analysis research community; document understanding; Books; Character recognition; Investments; Libraries; Natural languages; Optical character recognition software; Packaging; Redundancy; Text analysis; Turning;
Conference_Titel :
Document Analysis and Recognition, 2007. ICDAR 2007. Ninth International Conference on
Conference_Location :
Parana
Print_ISBN :
978-0-7695-2822-9
DOI :
10.1109/ICDAR.2007.4377029