For those following the #AutomaticTextRecognition course, this is the last course in the curriculum, reviewing the final steps and how to make the data reuseable! Check it out this #TrainingTuesday 😻

#DataReuse #ATR #OpenScience

➡️ https://campus.dariah.eu/resources/hosted/automatic-text-recognition-atr-end-formats-and-reusability

British Library Digital Scholarship Blog: Automatic Text Recognition in Cultural Heritage Institutions survey: a brief analysis and a published dataset. “A few months ago, we circulated a brief survey to understand how other institutions use Automatic Text Recognition and to discuss the creation of a working group on the subject… I am happy to report that the anonymised data are available […]

https://rbfirehose.com/2025/07/16/automatic-text-recognition-in-cultural-heritage-institutions-survey-a-brief-analysis-and-a-published-dataset-british-library-digital-scholarship-blog/

Automatic Text Recognition in Cultural Heritage Institutions survey: a brief analysis and a published dataset (British Library Digital Scholarship Blog) | ResearchBuzz: Firehose

ResearchBuzz: Firehose | Individual posts from ResearchBuzz

Last year we brought you the first part of the '#AutomaticTextRecognition' curriculum. Now in an improved format we bring part 2: #ATR - Where and How to Get Images #TrainingTuesday #DHTools

➡️ https://campus.dariah.eu/resources/hosted/automatic-text-recognition-atr-video-2-where-and-how-to-get-images

Automatic Text Recognition (ATR) - Where and How to Get Images

This tutorial explores where and how to find, create, and collect images of textual material, a crucial initial step in any process using Automatic Text Recognition (ATR).

Today, I will present our progress w/ the bilingual #DigitalScholarlyEdition of the #Danish #EthicaComplementoria prints from 1674 + 1678!
I'm happy to be invited to speak for the #Bookhistory research group at #UniOslo.
We've successfully transcribed & tagged 600+ pages (using #Transkribus for #AutomaticTextRecognition helped tremendously!) & are about to map them onto the #DeutschesTextarchiv #DTA base format. We'll make some adjustments for publication w/ #Bokselskap https://www.bokselskap.no/
Les gratis: «Hello world!» av

Yesterday, I taught the 1st hands-on workshop for the #BærUt #SustainableDSEs network!
I introduced #AutomaticTextRecognition w/ #Transkribus to 20 scholars who brought projects ranging from #EgyptianArabic to #Coptic #Ukrainian #Polish #Hebrew #Danish #Norwegian #English #Latin. Older prints & many handwritten materials. From as early as C11th to as late as mid C20th. https://www.ub.uio.no/english/courses-events/events/dsc/2024/digital-scholarship-days/06-transkribus.html
We had a blast & an organisational membership of the #UniversityOfOslo #Library is in the making, too!
Automatic Text Recognition for Historical Documents - University of Oslo Library

Make historical manuscripts and prints from any era and in any language and script machine-readable with the web application Transkribus

🧵 2/ #ResearchSupportPartnershipUiO For the spring, I have been invited to co-teach a BA class on #EarlyModern #EnvironmentalHistory
I will introduce data management & use #Zotero & #Tropy for managing bibliographical data and digitised documents.
At a later point, I will guide students through a workflow of #AutomaticTextRecognition w/ #Transkribus to translation w/ #UniOslo #ChatGPT4. We will look into biases and snares when it comes to using these tools for working with/ historical sources.
🧵 2/ #ResearchSupportPartnershipUiO I often get asked about how to quickly search through (handwritten) archival documents. Depending on how many documents we are talking about, there certainly are quicker ways then reading them! But setting up a workflow for #Digitisation, #AutomaticTextRecognition #QualityAssurance aren't done quickly either! Accessible tools like #Transkribus can help a lot here, but they can't do magic. So: plan enough time for these tasks and don't expect 100% accuracy!
🆕 #deeplearning models are changing the game for text recognition: OCR, ICR, HTR are outdated concepts. We now speak of #ATR (#automatictextrecognition): multi-script, multilingual https://teklia.com/blog/202212-atr/
👉 Discover #ocelus, our new ATR API : https://ocelus.teklia.com
Teklia - Automatic Text Recognition - The convergence between OCR and HTR technologies