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.

[dana_w]

Originally Posted by 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.

I totally understand the constraints of limited spare time, so I completely respect where you're coming from.

Currently, I'm planning to simply input data and fine-tune the data structures for my own needs, but it would be fantastic to have others weigh in with their insights and utilize these structures as well.

[kronckew]

I asked MS Copilot AI:


Write a presentation on categorizing sword collecting and categorization.

Originally Posted by Copilot

Sure, here’s a presentation outline on the fascinating world of sword collecting and its categorization.

The Art and Science of Sword Collecting

Introduction

• Hook: The allure of swords is timeless, captivating generations with their historical significance, craftsmanship, and aesthetic appeal.
• Purpose: This presentation explores the methods of categorizing swords for collectors, examining different criteria and highlighting key examples.

I. Historical Periods

• Ancient Swords: Bronze Age, Iron Age, and early civilizations.
  • Examples: Egyptian khopesh, Greek xiphos.
• Medieval and Renaissance Swords: European swords from the Dark Ages to the Renaissance.
  • Examples: Viking swords, longswords, rapiers.
• Modern Era Swords: 18th century to present.
  • Examples: Military sabres, ceremonial swords.

II. Geographical Regions

• European Swords:
  • Examples: Scottish claymore, Italian schiavona.
• Asian Swords:
  • Examples: Japanese katana, Chinese jian.
• Middle Eastern Swords:
  • Examples: Persian shamshir, Arabian saif.

III. Functional Classification

• Combat Swords:
  • Features: Designed for warfare and personal defense.
  • Examples: Broadsword, cutlass.
• Ceremonial Swords:
  • Features: Decorative, often used in rituals or as status symbols.
  • Examples: Officer's swords, coronation swords.
• Sporting Swords:
  • Features: Used in fencing and martial arts.
  • Examples: Foil, epee, sabre.

IV. Blade Types and Designs

• Straight Blades:
  • Features: Typically for thrusting.
  • Examples: Rapier, arming sword.
• Curved Blades:
  • Features: Designed for slashing.
  • Examples: Scimitar, falchion.
• Specialized Blades:
  • Features: Unique shapes for specific uses.
  • Examples: Kris, kukri.

V. Material and Craftsmanship

• Materials:
  • Examples: Damascus steel, folded steel.
• Crafting Techniques:
  • Examples: Forging, pattern welding, tempering.

VI. Collectors’ Considerations

• Authenticity and Provenance:
  • Importance: Verifying the sword's history and originality.
• Condition and Restoration:
  • Importance: Maintaining and preserving the sword's integrity.
• Market Value and Investment:
  • Factors: Rarity, historical significance, craftsmanship.

Conclusion

• Summary: The categorization of swords enriches the collecting experience, allowing enthusiasts to appreciate the diversity and heritage of these remarkable artifacts.
• Closing Thought: Whether a collector or admirer, understanding the categories of swords enhances our connection to history and the art of weaponry.

Feel free to expand on these points, add visuals, or adjust based on your specific needs! Happy presenting! ��

I asked it to supply pictures, It told me to go find them myself. Guess I upset Copilot.

[dana_w]

kronckew, I only wish it were that easy.

To be compatible with the Semantic Web, one would be required to utilize already formally defined terms for classes and properties. For instance, established ontologies such as Dublin Core (DCMI Metadata Terms) and CIDOC CRM (CIDOC Conceptual Reference Model), which are commonly used in the domain of cultural heritage, provide a foundational framework.

Within these established ontologies, specific terms for classes (such as 'Physical object') and properties (like 'material', 'date of creation', etc.) have been defined and standardized. This standardized vocabulary is essential to ensure interoperability between different systems and datasets on the Semantic Web.

To extend this with a custom ontology for something like Bladed Weapons, one would need to align new classes and properties with those already defined in established ontologies using a resource template. Such alignment facilitates the integration of specialized data into the broader Semantic Web ecosystem, allowing for easier searching, querying, and analysis across diverse datasets.

Here is an example of an RDF Framework for Bladed Weapons in human readable format:



Were I run into issues is with specialty properties like those needed for folding knives. I'll ask the AI to help with those and end up with something like "Washers", "The material and configuration of pivot washers" which I am not sure is useful or correct.

blade:washers a rdf:Property ;
rdfs:label "Washers" ;
rdfs:comment "The material and configuration of pivot washers" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .


Here is the full Bladed Weapons Vocabulary/Ontology in machine readable turtle format:


@prefix dcterms: <http://purl.org/dc/terms/> .
@prefix owl: <http://www.w3.org/2002/07/owl#> .
@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#> .
@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#> .
@prefix vs: <http://www.w3.org/2003/06/sw-vocab-status/ns#> .
@prefix o: <http://omeka.org/s/vocabs/o#> .
@prefix blade: REMOVED

<https://collections.REMOVED/ns/blade/> a owl:Ontology ;
dcterms:title "Bladed Weapons Vocabulary" ;
dcterms:description " A specialized vocabulary for describing historical and modern bladed weapons" .

bladeagger a rdfs:Class ;
rdfs:label "Dagger" ;
rdfs:comment "Short-bladed weapon primarily for stabbing" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:Knife a rdfs:Class ;
rdfs:label "Knife" ;
rdfs:comment "Single-edged blade without guard assembly" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:Polearm a rdfs:Class ;
rdfs:label "Polearm" ;
rdfs:comment "Bladed weapon mounted on a long shaft" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:Sword a rdfs:Class ;
rdfs:label "Sword" ;
rdfs:comment "Long-bladed weapon with hilt assembly including guard" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:backspringType a rdf:Property ;
rdfs:label "Backspring Type" ;
rdfs:comment "The style and configuration of the blade retention spring" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:bladeLength a rdf:Property ;
rdfs:label "Blade Length" ;
rdfs:comment "Length of the blade from point to heel" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:bladeMaterial a rdf:Property ;
rdfs:label "Blade Material" ;
rdfs:comment "Material composition of the blade" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:bladeWidth a rdf:Property ;
rdfs:label "Blade Width" ;
rdfs:comment "Maximum width of the blade" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:bolsterStyle a rdf:Property ;
rdfs:label "Bolster Style" ;
rdfs:comment "The design and material of the bolsters or reinforcement pieces" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:closedLength a rdf:Property ;
rdfs:label "Closed Length" ;
rdfs:comment "The length of the knife when folded" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:decoration a rdf:Property ;
rdfs:label "Decoration" ;
rdfs:comment "Description of decorative elements and techniques" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:deploymentMethod a rdf:Property ;
rdfs:label "Deployment Method" ;
rdfs:comment "The method used to open or deploy the blade" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:edgeType a rdf:Property ;
rdfs:label "Edge Type" ;
rdfs:comment "Configuration of cutting edges (single, double, or partial)" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:frictionDevice a rdf:Property ;
rdfs:label "Friction Device" ;
rdfs:comment "Any mechanism used to maintain blade position through friction" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:fullerDetails a rdf:Property ;
rdfs:label "Fuller Details" ;
rdfs:comment "Description of grooves or fullers in the blade" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:guardStyle a rdf:Property ;
rdfs:label "Guard Style" ;
rdfs:comment "Type and design of the guard/crossguard" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:handleScale a rdf:Property ;
rdfs:label "Handle Scale" ;
rdfs:comment "The material and construction of handle covering plates" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:headType a rdf:Property ;
rdfs:label "Head Type" ;
rdfs:comment "Style and configuration of the polearm head" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:lockingSystem a rdf:Property ;
rdfs:label "Locking System" ;
rdfs:comment "The mechanism used to secure the blade in open position" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

bladepenLength a rdf:Property ;
rdfs:label "Open Length" ;
rdfs:comment "The total length of the knife when opened" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

bladeivotMechanism a rdf:Property ;
rdfs:label "Pivot Mechanism" ;
rdfs:comment "The type and construction of the blade pivot system" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

bladeommelType a rdf:Property ;
rdfs:label "Pommel Type" ;
rdfs:comment "Style and construction of the pommel" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:scabbardDetails a rdf:Property ;
rdfs:label "Scabbard Details" ;
rdfs:comment "Description of scabbard or sheath if present" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:shaftLength a rdf:Property ;
rdfs:label "Shaft Length" ;
rdfs:comment "Length of the wooden shaft or pole" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:slipjointType a rdf:Property ;
rdfs:label "Slipjoint Type" ;
rdfs:comment "The specific design of non-locking blade retention" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:spineProfile a rdf:Property ;
rdfs:label "Spine Profile" ;
rdfs:comment "The shape and configuration of the blade's spine" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:springMechanism a rdf:Property ;
rdfs:label "Spring Mechanism" ;
rdfs:comment "The type and configuration of any spring assistance" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:stopPin a rdf:Property ;
rdfs:label "Stop Pin" ;
rdfs:comment "The type and location of blade travel limiters" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:tangConstruction a rdf:Property ;
rdfs:label "Tang Construction" ;
rdfs:comment "Type and extent of the tang (full, partial, rat-tail)" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

blade:washers a rdf:Property ;
rdfs:label "Washers" ;
rdfs:comment "The material and configuration of pivot washers" ;
rdfs:domain o:Resource ;
vs:term_status "experimental" .

[dana_w]

Here is an example of using Claude AI to help create a Sword Resource Template, built upon my earlier Dagger Resource Template. This work would clearly benefit from having a group of knowledgeable contributors.