As I said, Bookshare uses human proofreaders. The books are scanned and, of course, there are scanning errors. Then human volunteers download the scanned copy and proofread it correcting the errors. The corrected copy is then uploaded and that is what goes into the Bookshare collection.
On 12/29/2011 3:50 PM, Edward Betts wrote: > Does the bookshare correction software maintain word page coordinates? > > On 2011-12-29 12:23, Roger Loran Bailey wrote: >> I have an idea. It might run into a problem with copyright issues, but I >> am not sure because I think it might come under the provisions in the >> copyright act that covers preparing books for use by the print impaired. >> I am not sure what it is, but I think Open Library has a relationship >> with Bookshare. Bookshare has human volunteers who proofread scans of >> books. I am one of them. Might it be possible for Open Library and >> Bookshare to share scanned books? That is, copies of books that are held >> by Bookshare could be turned over to Open Library to be posted as >> protected Daisy books and the scans that come from the Internet Archive >> could be turned over to Bookshare to be proofread by Bookshare >> volunteers. Then after they have been proofread and enter the Bookshare >> collection they could be copied and returned to Open Library to be >> posted as better copies of what was there before. Am I just fantasizing >> or might something like this be possible? >> >> On 12/29/2011 3:03 PM, Edward Betts wrote: >>> We don't currently have a system for recording the quality of the OCR or >>> correcting mistakes. >>> >>> As you point out the OCR doesn't properly handle blackletter type. >>> >>> A system for correcting OCR is often requested, conceptually it is quite >>> simple. Just a web page that shows the page image and a way to edit the >>> text. We keen to maintain page coordinate information for each word so >>> that we can highlight words in the book reader and search inside. This >>> makes the problem more difficult. >>> >>> We would like to build a correction system, but we don't have the resources. >>> >> _______________________________________________ >> Ol-discuss mailing list >> [email protected] >> http://mail.archive.org/cgi-bin/mailman/listinfo/ol-discuss >> To unsubscribe from this mailing list, send email to >> [email protected] > _______________________________________________ > Ol-discuss mailing list > [email protected] > http://mail.archive.org/cgi-bin/mailman/listinfo/ol-discuss > To unsubscribe from this mailing list, send email to > [email protected] _______________________________________________ Ol-discuss mailing list [email protected] http://mail.archive.org/cgi-bin/mailman/listinfo/ol-discuss To unsubscribe from this mailing list, send email to [email protected]
