Skip to main content

ETHNOS_APP

Home • Search • Journals • List 0

Automatic ceramic identification using machine learning. Lusitanian amphorae and Faience. Two Portuguese case studies

Bibliographic Data

ID19553702
AuthorsJoel Santos (0000-0002-5796-9213, corresponding author), Diogo A P Nunes (0000-0002-6614-8556, Instituto Superior Técnico), Ruslan Padnevych (Universidade Nova de Lisboa), José Carlos Quaresma (0000-0003-3139-1975, University of Lisbon), Martim Lopes (0000-0001-9261-7240, University of Lisbon), Joana Gil (0000-0001-9301-6797, University of Lisbon), João Pedro Bernardes (0000-0002-4091-5833, University of Algarve), Tânia Manuel Casimiro (0000-0002-9471-6194, University of Lisbon)
Year2024
Volume10
Issue1
Publication date2024-12-31
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueSTAR Science & Technology of Archaeological Research (JOURNAL)
Journal identifiersISSN: 2054-8923 • E-ISSN: 2054-8923
PublisherInforma UK Limited (PUBLISHER • GB)
DOI10.1080/20548923.2024.2343214
OpenAlexW4396975644
LanguageEN
Citations received1
References cited28

This article presents a novel approach to classifying archaeological artefacts using machine learning, specifically deep learning, rather than relying on traditional, time-consuming human-based methods. By employing Convolutional Neural Networks (CNNs), this approach aims to expedite and enhance the identification process, making it more accessible to a wider audience. The study focuses on two types of artefacts- Roman Lusitanian amphorae (2nd-5th centuries) and Portuguese faience (16th-18th centuries)- chosen for their diversity. While Lusitanian amphorae lack decoration, Portuguese faience poses challenges with subtle colour variations. The study demonstrates the potential of this approach to overcome these hurdles. The paper outlines the methodology, dataset creation, and model training, emphasizing the importance of extensive data and computational resources. The ultimate objective of this research is to develop a mobile application that utilizes image classification techniques to accurately classify ceramic sherds and bring about a significant transformation in archaeological classification

Archaeology · Convolutional neural network · Geography · Portuguese · 3D Surveying and Cultural Heritage · Archaeological Research and Protection · Computer Science · Cultural Heritage Materials Analysis · Artificial Intelligence · Ecology

  • Chronological classification of Ming and Qing dynasty ceramics images based on an enhanced ResNet50 model

    Open Access•Lihua Yang, Wenbo Zhou et al.•STAR Science & Technology of…•2025

  • Archaeological Theory in the New Millennium

    Oliver J T Harris, Craig Cipolla et al.•Archaeological Theory in the New…•2017

  • Automated detection of archaeological mounds using machine-learning classification of multisensor and multitemporal satellite data

    Open Access•Hector A Orengo, Francesc C Conesa et al.•Proceedings of the National…•2020

  • Deep learning

    Open Access•Yann LeCun, Yoshua Bengio et al.•Nature•2015

  • A deep-learning model for predictive archaeology and archaeological community detection

    Open Access•Abraham Resler, R Yeshurun et al.•Humanities and Social Sciences…•2021

  • A ânfora vinária lusitana 3

    Open Access•José Carlos Quaresma, Joel Santos et al.•SAGVNTVM Papeles del Laboratorio…•2023

  • An Open System for Collection and Automatic Recognition of Pottery through Neural Network Algorithms

    Open Access•Maria Letizia Gualandi, Gabriele Gattiglia et al.•Heritage•2021

  • The automatic recognition of ceramics from only one photo

    Open Access•Francesca Anichini, Nachum Dershowitz et al.•Journal of Archaeological Science…•2021

  • Application of pattern recognition in detection of buried archaeological sites based on analysing environmental variables, Khorramabad Plain, West Iran

    Open Access•Siyamack Sharafi, Sajjad Fouladvand et al.•Journal of Archaeological Science…•2016

  • Large Language Models and Generative AI, Oh My

    Open Access•Peter J Cobb•Advances in Archaeological Practice•2023

  • The Accuracy and Adequacy of In-Field Artifact Analysis

    Open Access•Michael Heilen, Jeffrey H Altschul•Advances in Archaeological Practice•2013

  • Developing the ArchAide application

    Open Access•Francesca Anichini, Francesco Banterle et al.•Internet Archaeology•2019

  • Applications of deep learning to decorated ceramic typology and classification

    Open Access•L M Pawlowicz, C E Downum•Journal of Archaeological Science•2021

  • Unsupervised clustering of Roman potsherds via Variational Autoencoders

    Open Access•Simone Parisotto, Ninetta Leone et al.•Journal of Archaeological Science•2022

  • A burning question – Using an intelligent grey literature search engine to change our views on early medieval burial practices in the Netherlands

    Open Access•Alex Brandsen, Femke Eline Lippok et al.•Journal of Archaeological Science•2021

  • A deep variational convolutional Autoencoder for unsupervised features extraction of ceramic profiles. A case study from central Italy

    Open Access•L Cardarelli•Journal of Archaeological Science•2022

  • Learning feature representation of Iberian ceramics with automatic classification models

    Open Access•Pablo Navarro, Celia Cintas et al.•Journal of Cultural Heritage•2021

Unique citing works1
Citations per year1
Citation span2025 - 2025 (1)
Citation velocityrecent
Highly citedNo
Citation typesNeutral: 1
Ethnos_APP • Open Source Project • MIT License • Frontend v2.0.0 • Privacy and Cookies • API Documentation: api.ethnos.app/docs • API Source Code: GitHub • DOI: 10.5281/zenodo.17049435 • Frontend Source Code: GitHub • DOI: 10.5281/zenodo.17050053 • cruz.rio.br • Expectantes Misericordiae