The Role of Generative Systems in Historical Photography Management: A Case Study on Catalan Archives

TL;DR

This paper explores how generative AI systems can improve the description and management of historical photographs in Catalan archives, addressing language and contextual challenges in heritage image annotation.

Contribution

It presents a case study on using transfer learning for captioning models tailored to historical Catalan photographs, highlighting practical adaptation strategies.

Findings

Transfer learning improves captioning accuracy for historical images.

Visual and linguistic adaptation enhances model relevance.

Guidelines for applying generative systems to heritage archives.

Abstract

The use of image analysis in automated photography management is an increasing trend in heritage institutions. Such tools alleviate the human cost associated with the manual and expensive annotation of new data sources while facilitating fast access to the citizenship through online indexes and search engines. However, available tagging and description tools are usually designed around modern photographs in English, neglecting historical corpora in minoritized languages, each of which exhibits intrinsic particularities. The primary objective of this research is to study the quantitative contribution of generative systems in the description of historical sources. This is done by contextualizing the task of captioning historical photographs from the Catalan archives as a case study. Our findings provide practitioners with tools and directions on transfer learning for captioning models based on visual adaptation and linguistic proximity.