Extracting maps of meaning from archival data: testing the applicability of AI-based spectral clustering on multiband images of historic cartographic collections

Lucia Pereira-Pardo; Florence Liggins; Luke Butler; Sotiria Kogou; Haida Liang

doi:10.1117/12.2593910

13 December 2020 Extracting maps of meaning from archival data: testing the applicability of AI-based spectral clustering on multiband images of historic cartographic collections

Lucia Pereira-Pardo, Florence Liggins, Luke Butler, Sotiria Kogou, Haida Liang

Author Affiliations +

Proceedings Volume 11784, Optics for Arts, Architecture, and Archaeology VIII; 1178406 (2020) https://doi.org/10.1117/12.2593910
Event: SPIE Optical Metrology, 2021, Online Only

Abstract

While heritage science in museums usually focuses on the analysis of a single or a few iconic objects, material analysis of archival collections often deals with documents at mass-scale. In this setting, automation of data acquisition and data processing becomes particularly relevant. The analysis of a collection of Tudor maps of Ireland from the National Archives, London, serves as a case study to both test the applicability, and to optimise the methodology, of AI-based spectral clustering on data extracted from a commercial multiband imaging system, used typically for single-band and colour RGB imaging of archival documents, manuscripts and artworks on paper. The clusters revealed important information about the maps’ materiality, such as highlighting the different composition of painted areas within and across maps that appeared very similar in colour with the naked eye or differentiating original ink from later annotations, for instance. The clusters guided the selection of areas for further spectroscopic point analysis, both to check the performance of the algorithm and to interpret the material composition of the different clusters, with the ultimate goal of shading light on Tudor mapmaking practices. Strengths and aspects to be optimised in the methodology are finally discussed.

Conference Presentation

Citation Download Citation

Lucia Pereira-Pardo, Florence Liggins, Luke Butler, Sotiria Kogou, and Haida Liang "Extracting maps of meaning from archival data: testing the applicability of AI-based spectral clustering on multiband images of historic cartographic collections", Proc. SPIE 11784, Optics for Arts, Architecture, and Archaeology VIII, 1178406 (13 December 2020); https://doi.org/10.1117/12.2593910

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
PRESENTATION

WATCH
PRESENTATION SAVE TO MY LIBRARY

GET CITATION

KEYWORDS

Imaging systems

Data acquisition

Imaging spectroscopy

Raman spectroscopy

Reflectance spectroscopy

Scanners

Spectroscopy

Show All Keywords

Keywords/Phrases

Search In:

Publication Years