[new resource]: Slides and Code Materials for video school

[sarahalang]

Title of the resource

Computer Vision for Digital Humanists

Resource type

Hosted Resource

Authors, editors and contributors

Sarah A. Lang (contributor and PI), Sean Winslow (Co-PI), Suzana Sagadin (contributor), Sarah-May Lang (contributor), Angelos Nicolaou (contributor), Nicolas Renet (contributor), Niklas Tscherne (contributor), Daniel Luger (contributor), Germaine Götzelmann (contributor)

Topics (keywords)

Computer Vision, Machine Learning, Deep Learning, DH

Learning outcomes

The self-learning class "Computer Vision for Digital Humanists" consists of YouTube videos, slide decks and Jupyter Notebooks. It will teach you to learn:

• computer vision & deep learning basics
• how to create your own ground truth for supervised learning
• how to interpret & evaluate results of computer vision algorithms
• guidelines on how to best handle Humanities data within CV
• image management with Tropy
• pre-processing your data set in python
• moving from a first hello world 'mini model' to real-life ML

Abstract

The foundational skills in Distant Viewing and computer vision are increasingly relevant in the Digital Humanities, yet educational resources are often aimed at those with a background in computer science and statistics. For example, machine learning and digital image processing are fundamental to the Computational Humanities, but many scholars in the Digital Humanities lack accessible training in these areas.

The goal of this project was to create a focused course enabling students to acquire essential skills in computer vision, specifically tailored for Digital Humanists. Upon completing this course, students will possess a foundational understanding of digital image representation, computer vision methodologies, and machine learning techniques, all contextualized within a Digital Humanities framework.

This class is part of the project "Computer Vision for Digital Humanists" and licensed Creative Commons BY NC SA. This project (2023) was funded by CLARIAH-AT with the support of BMBWF. It was made possible by major contributions from the ERC DiDip project (From Digital to Distant Diplomatics). The video was produced by Moving Stills .

The goal of the project "Computer Vision for Digital Humanists" was the creation of educational self-learning resources on Computer Vision specifically for Digital Humanities, consisting of slide decks, Jupyter Notebooks with practical exercises in Python as well as teaching videos ( see the YouTube playlist. They cover a range of topics from the basics of computer vision and machine learning to training custom deep learning models for one's own historical data.

[VickyGarnett]

Hi @sarahalang - thanks for sending these proposals in. I wonder if we could try to arrange a time to have a chat about these proposed contributions so I can get a better idea of what you have, and we can discuss what might work best.

Thanks

Vicky

[VickyGarnett]

After discussion, we're changing this from a 'hosted resource' to an 'Event'

[VickyGarnett]

Hi @sarahalang - all the people associated with this event are now in the system, and you can proceed to drafting it up in the CMS https://campus.dariah.eu/docs/using-the-content-management-system :)