Modernizing the Documentation of Historical Weapons Collections

[dana_w]

Fellow collectors,

I'm working on a project to preserve and share information about my father's (Frederick Eugene "Jack" Williams III) collection of antique weapons, and I'd like to invite you to be part of a larger initiative this could become.

Screenshot 1: Current weaponscollector.com site


A small portion of the collection has been documented at weaponscollector.com, but I've been challenged by how to best organize and document the pieces.

Screenshot 2: New Omeka-S based site under development


I'm rebuilding the site using Omeka-S, a platform designed for digital collections and museums. The exciting part is that I'm developing a standardized way of describing weapons that anyone could use for their own collection. It combines:

1. Standard museum documentation practices (using CIDOC CRM)
2. General cultural heritage properties (from the Getty Art & Architecture Thesaurus)
3. Specialized classification systems for different weapon types

Weapons Vocabulary Class Diagram from above


The diagram shows how we're organizing different weapon types and their properties. For example, a sword entry would include both general properties (materials, provenance, markings) and specific details (blade length, guard style, pommel type).

This approach means:

• Each piece can be thoroughly documented
• Information can be easily shared between collections and databases
• The site works well on phones and tablets
• Data can be used by researchers and institutions
• Other collectors can use the same system for their collections

The Vision:
Imagine if multiple collectors used this same system to document their collections. We could:

• Create a network of virtual museums
• Make it easier to research and compare pieces across collections
• Preserve detailed information about pieces even after they change hands
• Build a valuable reference resource for the community

This is where you come in:
I'd really appreciate your expertise on what properties and classifications would be most useful for different weapon types. For instance:

• Are there important characteristics missing from any category?
• Should certain weapon types be classified differently?
• What measurements or details do you find most valuable when documenting pieces?
• Would you consider using this system for your own collection?

For those interested in the technical details:

• About Omeka-S: https://omeka.org/s/
• About CIDOC CRM: https://www.cidoc-crm.org/
• About DPLA: https://dp.la/

Thank you for any suggestions on improving this system. The goal is to create something that serves both individual collectors and the broader community while preserving the history of these fascinating pieces.

Best regards,
Dana

[werecow]

Interesting! I have a background in AI and for a while I've been thinking about doing a data science project involving sword collecting. A friend from the forums has also indicated that he's interested in joining in.

I'd be particularly interested in seeing if we can create a system for automated recognition of either images of swords, or even better, images of marks and decorations, or at least an image search for similar images that could be of help in identifying the markings in question. But right now I'm not sure where to get good training data (it would require a pretty extensive annotated database of images and metadata).

Anyway, it's not well thought out at the moment but when it takes a more concrete form I might contact you.

[dana_w]

Originally Posted by werecow

Interesting! I have a background in AI and for a while I've been thinking about doing a data science project involving sword collecting. A friend from the forums has also indicated that he's interested in joining in.

I'd be particularly interested in seeing if we can create a system for automated recognition of either images of swords, or even better, images of marks and decorations, or at least an image search for similar images that could be of help in identifying the markings in question. But right now I'm not sure where to get good training data (it would require a pretty extensive annotated database of images and metadata).

Anyway, it's not well thought out at the moment but when it takes a more concrete form I might contact you.

Thank you for your interest! Recent advances provide an exciting opportunity to combine traditional cultural heritage documentation with AI/ML capabilities. The semantic web work done by museums and cultural institutions over the past decades has created a strong foundation of structured data and standardized vocabularies that we can build upon.
While AI has become incredibly powerful at extracting structure from unstructured data, having well-organized source data is still crucial for training effective models. The CIDOC CRM ontology and Getty vocabularies I'm using provide exactly the kind of rich, structured relationships that can help train and validate AI systems.

I've spent time fine-tuning both vision and text models using LORA adapters, and I'd be very interested in collaborating on applying these techniques to weapon classification and mark identification. The standardized documentation approach I'm developing could help provide the kind of consistent, well-labeled training data that's often the biggest challenge in these projects.

Let me know if you'd like to discuss this further as your ideas take shape. There could be some interesting opportunities to combine our work.

[awdaniec666]

Wonderful! I wrote about this topic in the Glad:

https://thegladiological.com/2024/09...ms-and-armour/

[dana_w]

Originally Posted by awdaniec666

Wonderful! I wrote about this topic in the Glad:

https://thegladiological.com/2024/09...ms-and-armour/

Wow! That is a great article. Have you had a chance to look at Omeka-S? It is Open Source and well documented. The most challenging part of using it is getting up to speed on how it uses the W3C Web Ontology Language (OWL). a Semantic Web language designed to represent rich and complex knowledge about things, groups of things, and relations between things.

[awdaniec666]

I had a look, but this is something for somebody with more spare time than I do have - I regret not being able to write and publish a single article at the moment

I do however fully backup this project. If you need publicity through the Glad with some kind of beta version just let me know.