Modernizing the Documentation of Historical Weapons Collections

[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.