Saving Cultural Heritage with Digital Make-Believe: Machine Learning and Digital Techniques to the Rescue

Yasser, A, M, Clawson, Kathy, Bowerman, Chris and Lévêque, M (2017) Saving Cultural Heritage with Digital Make-Believe: Machine Learning and Digital Techniques to the Rescue. HCI '17: Proceedings of the 31st British Computer Society Human Computer Interaction Conference (97). pp. 1-5.

SavingCulturalHeritage_SURE.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (734kB) | Preview

Search Google Scholar


The application of digital methods for content-based curation and dissemination of cultural heritage data offers unique advantages for physical sites at risk of damage. In areas affected by 2011 Arab spring, digital may be the only approach to create believable cultural experiences. We propose a framework incorporating computational methods such as: digital image processing, multi-lingual text analysis, and 3D modelling, to facilitate enhanced data archive, federated search, and analysis. Potential use cases include experiential search, damage assessment, virtual site reconstruction, and provision of augmented information for education and cultural preservation. This paper presents initial findings from an empirical evaluation of existing scene classification methods, applied to detection of cultural heritage sites in the Palmyra region. Results indicate that deep learning offers an appropriate solution to semantic annotation of publicly available cultural heritage image data.

Item Type: Article
Additional Information: British Human Computer Interaction Conference; Sunderland University, St Peter's Campus; 3 - 6 Jul 2017
Subjects: Computing > Artificial Intelligence
Computing > Human-Computer Interaction
Divisions: Faculty of Technology > School of Computer Science
Depositing User: Kathy Clawson
Date Deposited: 03 Aug 2017 08:35
Last Modified: 15 Dec 2020 14:00
ORCID for Kathy Clawson: ORCID iD

Actions (login required)

View Item View Item


Downloads per month over past year