Exploring Handwritten Text Recognition for Manuscript Studies

“Join the Penn Libraries’ Manuscript Collections as Data Research Group and friends on Monday, January 26th from 3-4pm in Williams Hall 623 (or Zoom) for an overview of ongoing efforts to explore AI & computer vision applications for historic document study. This discussion will present the work of two 2025-2026 Schoenberg Institute for Manuscript Studies (SIMS) Graduate Student Fellows and a 2025 Penn Libraries Data Science and Society Research Assistant exploring Handwritten Text Recognition technologies for use on a variety of historic and archival documents for future in-depth research. This conversation will highlight the challenges and opportunities for using automated tools such as Kraken and eScriptorium to produce machine-readable textual corpora in an informal setting, with discussion focusing on the benefits and limitations of some tools and techniques currently extant. This event will be of interest to researchers of all levels investigating historic textual corpora and interested in applying cutting-edge research techniques to assist in their scholarship.