BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//www.dariah.eu//Events//EN
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:019e45f2-2c5a-731f-b9ed-ad355971c79f@www.dariah.eu
DTSTAMP:20260520T151239Z
DTSTART;VALUE=DATE:20250901
DTEND;VALUE=DATE:20250906
SUMMARY:ATRIUM Summer School on Automatic Text Recognition
DESCRIPTION:We are pleased to announce the ATRIUM Summer School on Automati
 c Text Recognition\, taking place from September 1–5\, 2025\, at the DAR
 IAH Coordination Office in Berlin. This intensive five-day training event 
 is designed for researchers\, digital humanists\, and cultural heritage pr
 ofessionals who want to explore and implement state-of-the-art OCR (optica
 l character recognition) and HTR (handwritten text recognition) technologi
 es in their projects.\n\nYou have automatically extracted text from digiti
 zed material\, but are not satisfied with the output? You want to improve 
 the accuracy of your transcribed data? You know how to apply an existing m
 odel to your documents but want to go further and learn how to fine-tune a
  model or create one from scratch? You work in a project team that deals w
 ith complex data needing particular attention in the Automatic Text Recogn
 ition process in order to address a specific difficulty? You want to tackl
 e advanced recognition issues? Then the ATRIUM Summer School on ATR is mad
 e for you.\n\nAbout the Summer School\n\nThe ATRIUM Summer School will pro
 vide an in-depth approach to automatic text recognition with a focus on pr
 actical applications in concrete research scenarios. Participants will gai
 n insights into the latest developments in OCR and HTR\, focusing on open-
 source tools such as eScriptorium and workflows that facilitate the digiti
 zation and analysis of historical and modern texts.\n\nDuring one week\, t
 he trainer team will alternate methodological input and supervision of han
 ds-on sessions for the participants to improve their automatic text recogn
 ition pipelines. Input will cover not only the manipulation of pre-process
 ing\, segmentation\, layout analysis\, and post-processing\, but also data
  management\, empowering participants to achieve concrete goals in terms o
 f the management\, processing and reusability of their data within the dur
 ation of the summer school and beyond.\n\nWhat to expect?\nExpert-led lect
 ures and practical sessions on ATR tools and techniques\nHands-on training
  with open-source platforms such as eScriptorium\nCase studies showcasing 
 real-world applications in research and cultural heritage\nOpportunities f
 or participants to work on their own projects and receive expert feedback\
 nNetworking with peers and leading scholars in the field\nWho should apply
 ?\nResearchers in the humanities and social sciences\nDigital humanists an
 d computational linguists\nArchivists\, librarians\, and cultural heritage
  professionals\nDevelopers and data scientists working with textual data\n
 \nBasic familiarity with digital humanities and at least some experience w
 ith OCR/HTR is required\, as we will quickly jump into practice.\n\nWe wil
 l consider applications from teams of up to two members working on the sam
 e project requiring an automatic text recognition pipeline\, provided they
  have well-defined objectives for the summer school week\, and a dataset t
 o work on.\n\nTechnical Requirements\n\nThe ATRIUM Summer School will supp
 ort you in processing and transcribing your documents. Therefore\, it is i
 mperative that you bring your own dataset\, such as scanned pages of the d
 ocuments you want to transcribe. Please ensure that the digitization is of
  good quality. The dataset should not contain images that are too noisy (a
 void blurry images\, stains\, tears\, etc.) as it would severely hinder th
 e recognition process. Finally\, although high resolution is not necessary
 \, a minimum resolution of 300 dpi is recommended to ensure recognition by
  the software.\n\nParticipants are expected to bring their own laptop.
LOCATION:Berlin\, Germany
URL:https://www.dariah.eu/events/atrium-summer-school-on-automatic-text-rec
 ognition
END:VEVENT
END:VCALENDAR