Machine Learning for Cultural Heritage: A Survey

TLDR

Machine Learning has progressed in Cultural Heritage from simple statistical models to deep learning, yet it remains unclear whether these advances truly improve performance or merely act as black boxes. This survey aims to identify theoretical changes that make ML algorithms suitable for Cultural Heritage applications. The authors review the literature, examining theoretical modifications, application contexts, feature engineering, preprocessing, and the distribution of supervised, semi‑supervised, and unsupervised methods to assess their suitability for Cultural Heritage. The analysis reveals that, despite extensive use of ML in Cultural Heritage, adoption remains limited due to challenges in algorithm suitability and interpretability.

Abstract

The application of Machine Learning (ML) to Cultural Heritage (CH) has evolved since basic statistical approaches such as Linear Regression to complex Deep Learning models. The question remains how much of this actively improves on the underlying algorithm versus using it within a 'black box' setting. We survey across ML and CH literature to identify the theoretical changes which contribute to the algorithm and in turn them suitable for CH applications. Alternatively, and most commonly, when there are no changes, we review the CH applications, features and pre/post-processing which make the algorithm suitable for its use. We analyse the dominant divides within ML, Supervised, Semi-supervised and Unsupervised, and reflect on a variety of algorithms that have been extensively used. From such an analysis, we give a critical look at the use of ML in CH and consider why CH has only limited adoption of ML.