Mary Shelley, rakt in i fånen!

The extraction of text from page images is a difficult engineering\ntask. Smudges on the physical books' pages, fancy fonts, old fonts,\ntorn pages, etc. can all lead to errors in the extracted text. (...)

Imperfect OCR is only the first challenge in the ultimate goal of\nmoving from collections of page images to extracted-text based books.\nOur computer algorithms also have to automatically determine the\nstructure of the book (what are the headers and footers, where images\nare placed, whether text is verse or prose, and so forth). Getting this\nright allows us to render the book in a way that follows the format of\nthe original book.

The technical challenges are daunting, but\nwe'll continue to make enhancements to our OCR and book structure\nextraction technologies. With this launch, we believe that we've taken\nan important step toward more universal access to books.