Online lecture 2: Using automatic transcription for processing historical sources

Lecturers: Adrià Molina (Computer Vision Center) & Joana Maria Pujadas-Mora (Open University of Catalonia & Center for Demographic Studies)

Content of the lecture: The aim of the lecture is to explore the development of a historical digital twin from demographic sources within a big data setup.

Objectives of the lecture:

1. Highlighting the legitimacy of using automatic methods on demographic sources.
2. Understanding the current challenges in applying AI to historical sources.
3. Overcoming challenges through handwriting recognition of population registers to build the BALL database.

Recommended reading:

• Pujadas-Mora, J. M., Fornés, A., Ramos Terrades, O., Chen, J., Valls-Fígols, M., & Cabré, A. (2022). The Barcelona Historical Marriage Database and the Baix Llobregat Demographic Database. From algorithms for handwriting recognition to individual-level demographic and socioeconomic data. Historical Life Course Studies, 2022, 12 (99).
• Molina, A., Terrades, O. R., & Lladós, J. (2024, August). Fetch-A-Set: A Large-Scale OCR-Free Benchmark for Historical Document Retrieval. In International Workshop on Document Analysis Systems (pp. 347-362). Cham: Springer Nature Switzerland.

You can download the presentation by Adrià Molina in .pdf.