- Javítás és szerviz
Print & Probability
Computational project for discovering historical printers.
Bemutatkozás
Print & Probability is an interdisciplinary, NEH- and NSF-funded project focused on book history, computer vision, and machine learning. The team, comprising book historians, statisticians, computer scientists, and librarians, develops methods for modeling material conditions of early modern print shops, such as fonts, damaged type, paper, inking, and imposition, to solve bibliographical mysteries. The project involves researchers from Carnegie Mellon University and the University of California, San Diego, and has produced tools like a fully searchable stopgap English Short-Title Catalogue (ESTC) following a cyberattack on the British Library, the Print & Probability Workbench REST API utilizing the Ocular OCR system, and a beta Coloring Book Paper Analysis Tool for investigating paper-stocks via remote IIIF images. The project acknowledges support from CMU Mellon Seed Grants, the National Science Foundation, and the National Endowment for the Humanities.
Szolgáltatások, tevékenységek
- Development of tools and methods for discovering letterpress printers
- Modeling material conditions of early modern print shops (fonts, damaged type, paper, inking, imposition)
- Providing a stopgap English Short-Title Catalogue (ESTC) that is fully searchable
- Providing the Print & Probability Workbench (Django-powered REST API for data transformation and tagging pipeline)
- Classification of characters using Ocular (historical OCR system)
- Coloring Book Paper Analysis Tool for generating and studying LUV or RBG color profiles for digitized book pages