Cold and rainy but good fun at the annual Science Day in Leuven where we demonstrated how anyone can easily collect and work creatively with high-quality images streamed from cultural organizations globally. #dvdw2025 #IMMARKUS
New in #IMMARKUS: when you import a #IIIF manifest, IMMARKUS now imports existing annotations (embedded or referenced) into your workspace.
We'd love to test with real-world examples. If you know of IIIF collections with annotations, let us know. Annotated manifests still seem rare in the wild...
With #IMMARKUS, you can already use popular AI services for image transcription. Now, you can also use them for translation! Transcribe a historic source, select the annotation—and translate it with a click.
Tried to use #IMMARKUS with new GPT-OSS model, via #HuggingFace inference providers. But either I'm missing something, or the model (or the providers?) don't support vision capabilities?
Model card doesn't seem to say anything specific about it... huggingface.co/openai/gpt-o...
On the left: a medieval manuscript, with overlaid annotations. On the right: the new IMMARKUS multi-select dialog user interface.
We are extending the multi-select options in #IMMARKUS! Merge and subtract selections, batch-tag and batch-delete, and (new!) compare annotation data side-by-side. The multi-select panel is getting a small facelift, too!
Screenshot of the new configuration dialog for using HuggingFace Spaces as transcription services in IMMARKUS.
Quick update: Plugging your own transcription service into #IMMARKUS via Hugging Face Spaces is now available for testing on our dev server!
It’s a bit DIY/hacky... But if you’re building your own HF Spaces, you’re probably ready for that 🙂 Ping me if you’d like to try it out!
A screenshot of the IMMARKUS transcription interface. The left side shows the document preview. The right side shows the configuration dialog for the (work-in-progress) "HuggingFace Spaces" integration.
Back to work after a short break & working on two new #IMMARKUS transcription extensions:
• Transcribe via HuggingFace Inference Providers
• Plug in your own HuggingFace Space!
The second one’s experimental... If you run your own Space and want to try it in IMMARKUS, give me a shout!
Because sometimes you want that extra bit of precision: Bezier curve drawing is coming—pixel-perfect annotations for #IMMARKUS, #liiive, and all tools powered by #Annotorious
It has come to my attention that some people (scandalously!) want to work with their image annotations OUTSIDE of #IMMARKUS. If you're so inclined, you might enjoy our upcoming copy-and-paste feature!
A screenshot of the IMMARKUS transcription wizard, showing the dropdown menu of service options.
If you haven’t checked in on #IMMARKUS lately—we’ve added even more transcription services. Run OCR or transcription using:
• Anthropic Claude
• Azure Computer Vision
• Google Gemini
• Google Vision
• LLaMA & Qwen via kluster.ai
• OCR.space
• OpenAI GPT
• Volcano Engine
More coming—stay tuned!
Small enhancement to #IMMARKUS’ Google Vision integration: You can now choose the level of detail when importing OCR results—words, paragraphs, or full blocks.
#OCR #IIIF #ImageAnnotation #DigitalHumanities
The IMMARKUS OCR tool, showing a digitized Chinese gazetteer page in the OCR preview and settings dialog.
The IMMARKUS annotation interface, showing an area selected on scanned atlas index page, and the corresponding automated transcription.
In our quest to make #OCR as easy to use as possible, we've added two new services to #IMMARKUS: Google Gemini and OpenAI GPT. (You’ll need your own API keys.)
Both return full-text transcriptions–no bounding boxes–so you have to select a region before running. Works with local images and #IIIF!
We’re adding more OCR and image annotation services to #IMMARKUS! Now available: Google Vision API — which actually works really well with historical materials, too. 👀 (Note: you’ll need to bring your own API key.)
New in #IMMARKUS: run OCR directly from your workspace!
• Submit full image or selected regions
• Run multiple passes, preview results
• Import word- or line-level annotations
• Works with local files and #IIIF
Got an OCR service we should support? Let us know!
🔗 immarkus.xmarkus.org
Well done @thejohnrylands.bsky.social on the #IIIF -- working with the primers and all your metadata in #IMMARKUS (immarkus.xmarkus.org) is a snap!
MapReader results out in the world!! This is such a fantastic combination of tooling. Can't wait to try #IMMARKUS with some of our work in progress :)
Aaaand… we’re already experimenting with bringing MapReader outputs into our #IMMARKUS annotation tool—for validation, cleanup, correction, and further analysis. (Seen here: a map with ~2,500 transcribed labels.) #ImageAnnotation #IIIF #Annotorious
The "smart scissors" selection tool in action: easily traces edges in the image by hovering over them with your mouse.
Screenshot of the IMMARKUS knowledge graph browsing interface.
Screenshot of IMMARKUS' main work area: the multi-image annotation view, with three images open and the annotation list in the right sidebar.
Haven't explored #IMMARKUS yet? Now’s a great time!
• New docs & screenshots
• Annotate images (local or IIIF)
• AI tools for faster annotating
• Build your own ontology & knowledge graph
• Open source, works in your browser
immarkus.xmarkus.org
#ImageAnnotation #IIIF #DigitalHumanities
#IMMARKUS update: our next release will complete our toolbox of smart drawing tools!
• Smart Scissors – trace edges, Photoshop-style.
• Edge Snap – snap to corners & lines for clean cutouts.
• Auto Select – smart one-click object selection.
Want to know more? Ping us! #IIIF #DigitalHumanities
Yay–that's starting to work pretty well! #IMMARKUS #OpenSeadragon #IIIF
And another one! ✂️ A smart selection tool powered by the "Intelligent Scissors" algorithm from OpenCV.js. This should make complex polygon annotation a breeze! Coming to #IMMARKUS (very) soon. #ImageAnnotation #IIIF
You should definitely check out the new documentation for #IMMARKUS–comprehensive, well-written & packed with useful screenshots. It's up to date with all our latest features (plus some peeks at what's coming next). Kudos to the @infralives.bsky.social team!
Working on some new drawing features ✍️ coming soon to #IMMARKUS: Boolean operations (merge and subtract shapes)! Plus: shapes can now have holes. #JavaScript #Annotorious #IIIF #OpenSeadragon
Wait... is that a new button in #IMMARKUS? 🪄 Yes! Click the magic wand for automatic object selection, powered by #SegmentAnything. Just point, click, and let AI do the work! Try it out and let us know what you think. #DigitalHumanities #IIIF
It's working pretty well & stable already. Users of #IMMARKUS will be able to test it before the end of the week 🚀. (Note that it does require a recent browser with WebGPU support–Chrome and Edge only so far, but not FF or Safari.)
Update: Smart object selection in zoomable images with #OpenSeadragon and #SegmentAnything! The next key challenge: Creating a seamless workflow—picking objects, refining shapes, and manually enhancing the outline. Stay tuned! #IMMARKUS #IIIF #DigitalHumanities #Maps
Progress! Refine and extend areas by adding points to #SegmentAnything queries. Plus, polygon smoothing for cleaner annotation shapes. Next up: making it work in OpenSeadragon… #IMMARKUS #DigitalHumanities #Annotorious
I'm excited! This time, it's not just a prototype: AI-powered selection tools are *actually* coming to #IMMARKUS as a feature – thanks to the great team at @infralives.bsky.social. #DigitalHumanities #IIIF #ImageAnnotation #Annotorious
🚀IMMARKUS 0.7.2🚀
Try the latest release of our semantic image annotation platform: immarkus.xmarkus.org
✨Highlights:
🔹 Enhanced entity relations & knowledge graph search
🔹 #IIIF support
Big thanks to @aboutgeo.bsky.social for making this happen! 👏
#IMMARKUS #IIIF #DigitalHumanities
The screenshot shows IMMARKUS's knowledge graph view, with an image selected. In the sidebar, below the image preview, you can see cropped annotation snippets, generated with the new cropping feature for Level 0 tilesets.
Feature alert! 🔍 #IMMARKUS can now crop arbitrary annotation regions from IIIF Level 0 tilesets—no image server needed! It fetches, stitches, and crops tiles on the fly, making static IIIF images as flexible as any other IIIF source.
