(he/him) Survived the Kulmbach Beast! 21km of pure pain and glory. Blog post with all the details here: https://open.substack.com/pub/hansamann/p/conquering-the-kulmbach-beast-a-spartan?r=1sq3ws&utm_campaign=post&utm_medium=web&showWelcomeOnShare=true
#SpartanRace #OCR
Verwaltet von:
#ocr
3 Beiträge3 Beteiligte0 Beiträge heute
If you haven’t checked in on #IMMARKUS lately (understandable—there’s been a lot going on!)—we’ve added even more transcription service options.
You can now run OCR or full-text transcription with a single click using:
• Anthropic Claude
• Azure Computer Vision
• Google Gemini
• Google Vision OCR
• LLaMA & Qwen via kluster.ai
• OCR.space
• OpenAI GPT
• Volcano Engine Doubao 1.5 Vision Pro
Try it out here: https://immarkus.xmarkus.org
Antwortete im Thread
@_DigitalWriter_ ist es eine alternative zu #paperlessngx?
In meinem Blogbeitag auf ETHeritage beschreibe ich, wie wir auf e-rara #NamedEntityRecognition und #NamedEntityLinking einsetzten.
I have a genuine AI problem which I can't find an easy solution for.
We use Google's Vision API to OCR inscription from photographs.
Most of the time it is great, but sometimes it includes homographic characters.
For example - https://openbenches.org/bench/38224
It has misdetected the letters in "ΤΟΝΙΑ" as Greek rather than Latin.
I can't send a language hint, because people upload images from all over the world.
Is there a good (preferably free) OCR which wouldn't make this mistake?
OpenBenchesIn Loving Memory of
ΤΟΝΙΑ
HENDRIKS
21st November 2023
Am Donnerstag referiert mein Kollege Roman Walt für mich an der #bibliocon25 zu #OCR und #NER #NEL auf e-rara – Danke Roman!
https://bid2025.abstractserver.com/program/#/details/presentations/525
#namedentityrecognition #namedentitylinking #ethbibliothek #erara
bid2025.abstractserver.comProgram
Delighted to announce that the paper on best practices in pre- and post-ATR for historical research that I co-authored with @koen_hufkens is now available on Zenodo:
https://zenodo.org/records/15703825
Big thanks to @hermes_datenkompetenzzentrum for funding our initial workshop at @DHLab_IEG earlier this year. It was nice to present our findings to a larger, international community at #dae2025 in Göttingen. #histodons #digitalhumanities #ocr #htr
ZenodoBest practices in pre- and post-ATR for historical researchBased on discussions and hands-on experiments conducted with the participants of a HERMES Bring Your Own Data Labs workshop hosted in Mainz in February 2025, this paper shares four key recommendations for (AI-supported) pre-and post-ATR (automatic text recognition) in historical research. The code used during the workshop and important observations are also published in the following GitHub repository:Barget, Monika (2025). Automated text recognition in historical research. [Github repository]. https://monikabarget.github.io/atr-historical-research/ The repository is work-in-progress and will be updated further.
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.)
On the Road
On Tuesday, as part of the @Textplus plenary at @unigoettingen, our FID showcased a poster and gave a presentation on digital age text corpora.
Neu im HERMES-Blog: Rückblick auf unsere erste Data Challenge!
Das Siegerteam zeigt eindrucksvoll, wie KI – konkret LLMs – auch unter Hardware-Beschränkungen für die Vorverarbeitung großer Datenmengen genutzt werden kann.
Jetzt den Beitrag lesen: 
https://hdl.hypotheses.org/2224
stole your image of a social media post, yadda yadda…
❝ COLLINS: “Tulsi Gabbard testified in March that the intelligence community said lran wasn't building a nuclear weapon.”
TRUMP: “l don't care what she said. | think they were very close to having one.” ❞
BTW: the #OCR app for #android is an absolute must have:
OCR - https://f-droid.org/packages/io.github.subhamtyagi.ocr
Antwortete im Thread
@NanetteRissler @dariaheu You seem to be the only Mastodonian posting on #dae2025 so far --- so I thought I should say hello! 
I am here to co-chair the #dariahTeach working group and to give a paper on #OCR and options to integrate #LLMs in the text recognition workflow. This paper is based on a workshop I gave with @koen_hufkens at @DHLab_IEG earlier this year.
We’re working on an extension that lets you send images to OCR services right from your #IMMARKUS workspace!
• Submit full images or selected regions
• Run multiple passes, preview results
• Import word- or line-level annotations
• Works with local files and #IIIF
Got an OCR engine or map-text service we should support? Reach out!
Or just need a flexible tool to annotate historical images? Try IMMARKUS: https://immarkus.xmarkus.org
#NormCap - Un #OCR gratuit pour #capturer directement le #texte, sans besoin de faire des #captures d’ #écran intermédiaires inutiles.
#NormCap est basé sur #Tesseract, le moteur OCR #opensource #foss de #Google qui reconnaît plus de 100 langues.
https://korben.info/normcap-ocr-gratuit-capture-texte-directement.html
Le site de KorbenNormCap - Un OCR gratuit pour capturer directement le texte | Le site de KorbenVous aussi vous avez déjà passé 10 minutes à retaper ligne par ligne un bout de code trouvé dans un screenshot de Stack Overflow ?
Félicitations, vous ...
This OCR model turns document images into clean markdown with tables, LaTeX and more. Your LLMs will thank you. #OCR #ML #DevTools https://huggingface.co/nanonets/Nanonets-OCR-s
huggingface.conanonets/Nanonets-OCR-s · Hugging FaceWe’re on a journey to advance and democratize artificial intelligence through open source and open science.
#HERMESDataChallenge : #DH-Forschung als kollaboratives Datenprojekt – mit Fokus auf Datenqualität, #OCR-Mängel & #KI-Vorverarbeitung. Große Datenmengen, wenig Ressourcen: Wie weit kommt man?
@hermes_datenkompetenzzentrum : https://hdl.hypotheses.org/2224
Humanities Data LiteracyRückblick auf die erste Data Challenge von HERMES: “Challenge the Newspaper Data!”In unserem ersten Blog-Beitrag zu dieser Data Challenge haben wir unser Konzept für das neue Format im Bereich der digitalen Geisteswissenschaften vorgestellt. Zudem haben wir die Aufgabenstellung unserer ersten Challenge präsentiert, die auf der Analyse von Zeitungsdaten aus dem Deutschen...
Bounty mit 11 Jahren bei Camp Canis Island auf Usedom. Im September 2021 war das. Ich wurde Blind-Date-mäßig mit einer Starterin gematcht, weil uns beiden die Teampartnerin weg gebrochen war. Und es war ein gutes Match! Ein Hindernislauf für Menschen und Hunde am Meer - das war schon was besonderes. Etappen am Strand, Hindernisse im Meer und dazu noch der schöne Wald an der Küste. Schade, dass die Location nicht mehr bespielt wird...
Foto/Pic: Van Luettjen
#Dogs #Hund #Hunde #DogsOfMastodon #DogsOfPixelfed #CampCanis #Hindernislauf #OCR #SUP #Schwimmen #Meer #Sea #Ostsee #BalticSea #Usedom #Sports #Hundesport #DogSports #SeniorDog #AlterHundNaUnd #Canicross
Bounty at Camp Canis Island on Usedom at the age of 11. That was in September 2021. I was matched with a starter in a blind date kind of way because both of us had lost our team partners due to illness. And it was a good match! An obstacle course for people and dogs by the sea – that was something special. Run on the beach, obstacles in the sea and the beautiful forest on the coast. It's a shame that the location is no longer used...
Foto/Pic: Van Luettjen
#Dogs #Hund #Hunde #DogsOfMastodon #DogsOfPixelfed #CampCanis #Hindernislauf #OCR #SUP #Schwimmen #Meer #Sea #Ostsee #BalticSea #Usedom #Sports #Hundesport #DogSports #SeniorDog #AlterHundNaUnd #Canicross
Bounty at Camp Canis Island on Usedom at the age of 11. That was in September 2021. I was matched with a starter in a blind date kind of way because both of us had lost our team partners due to illness. And it was a good match! An obstacle course for people and dogs by the sea – that was something special. Run on the beach, obstacles in the sea and the beautiful forest on the coast. It's a shame that the location is no longer used...
Antwortete your auntifa liza 
@blogdiva Oh snap! I didn't know such a beast was available, but that works a treat! At least as good as the main Mastodon web interface's 'detect text' function!
Thanks!