Hi-
Thanks for your message. I am not sure where you heard we were getting new OCR software. We changed our processors and therefore got new OCR software back in 2015, and have been using our new – much better – OCR software for all of our additional material to the CHNC since then – but we cannot, and have no plans to run the OCR process again on the 660,000 pages that were processed originally in the CHNC before our 2015 migration. The digitization and segmentation process for our collection is a very expensive process, and we do not have the funds required to re-do what has been done back when the technology was more primitive.
Right now we cannot correct errors in columns or article segmentation locally – but that is not necessarily always going to be the case. There are wonderful technological advancements happening all of the time – and when we are able to make these changes ad hoc locally – we will certainly do it. I would suggest keeping track of the errors you find and sending them to me (harper_r@cde.state.co.us)- and when we are in a position to make a change – we will do so based upon your information. I know it is not a real time solution – but I am confident that some day we will be able to make these changes.
Thanks again for letting me know your concern. We appreciate feedback from our users – and we hope to be able to grow the database in ways that will help you do what you need to do better with the database.
All the best –
Regan
.
.
