Re: [EXTERNAL EMAIL] Converting image of MARC to text MARC?

From: Terry Reese <reeset_at_nyob>
Date: Mon, 21 Jul 2025 14:02:47 -0700
To: CODE4LIB_at_LISTS.CLIR.ORG
Do you have an example.  I'm working on the templating for the MarcEdit AI
integration that works with openai, gemini or ollama (for local
processing).  I've not tested finished records -- mostly images of card
catalogs, documents (pdfs, docx, etc.), or digitized images.

--tr

On Mon, Jul 21, 2025 at 1:00 PM Blake, Wil <wil.blake_at_fcpl.org> wrote:

> Hello Erich,
>
> You might try MarcEdit. A 2015 project with links below has a
> semi-automated approach using text editing tools to make the data file
> acceptable to MarcEdit's "MarcMaker" feature. Good luck.
>
>
> MarcEdit Features
> https://marcedit.reeset.net/features
>
> Example Project, Fixing Marc Records
>
> http://www.meanboyfriend.com/overdue_ideas/2015/07/worked-example-fixing-marc-data-1/
>
> Project Part 2 Using a Text Editor to repair the data
>
> http://www.meanboyfriend.com/overdue_ideas/2015/07/worked-example-fixing-marc-data-2/
>
> Regards,
> Wil Blake
>
> -----Original Message-----
> From: Code for Libraries <CODE4LIB_at_LISTS.CLIR.ORG> On Behalf Of Hammer,
> Erich F
> Sent: Monday, July 21, 2025 3:14 PM
> To: CODE4LIB_at_LISTS.CLIR.ORG
> Subject: [EXTERNAL EMAIL] [CODE4LIB] Converting image of MARC to text MARC?
>
> Without going into details, we inherited a sizeable collection of physical
> materials from another library, and were only able to capture the unique
> MARC records in image (PDF) form.
>
> Visually, they are quite readable and obviously MARC (to a human eye).
> They are OCR'd, but as you can imagine, the text is in blocks that when
> collectively copied do not paste into any useable order that would allow us
> to process them.  Copy/pasting every little block of text into the right
> order would take as much time (likely more) than simply re-typing them all
> (although possibly with less error).
>
> Does anyone know of a way to automatically convert these into useable
> MARC?  It feels like something AI could do if trained, but I haven't a clue
> how to go about doing that.
>
> Thanks,
> Erich
>
>
> --
> Erich Hammer            Head of Library Systems
> erich_at_albany.edu         University Libraries
> 518-442-3891              University @ Albany
>
> "Belief gets in the way of learning."     -- Robert Heinlein
>
Received on Mon Jul 21 2025 - 17:01:46 EDT