Digital Applications in Archaeology and Cultural Heritage最新文献

{"title":"From manuscript inventories to data: Artificial intelligence and databases, a new chapter for the history of science at “G. Marconi” Central Library of the CNR","authors":"Santorsa Sara,&nbsp;Bartolucci Monia,&nbsp;Cilione Emanuela,&nbsp;Florio Isabella,&nbsp;Migliorelli Giorgia,&nbsp;Ranchino Maria Adelaide,&nbsp;Tiberi Luca","doi":"10.1016/j.daach.2025.e00459","DOIUrl":"10.1016/j.daach.2025.e00459","url":null,"abstract":"<div><div>Established in 1927, the “G. Marconi” Central Library of the National Research Council (CNR) has, from its inception, benefited from the legal deposit of Italian technical-scientific publications. This legacy has earned it the reputation of being Italy’s National Library of Science and Technology. This paper explores the evolving role of the digital librarian by focusing on a project to enhance and improve accessibility to the Library’s heritage through the analysis and digitisation of its manuscript inventory books (15/10/1931–10/01/1991). These volumes record a summary description of 205,683 bibliographic documents. By defining criteria for preservation, restoration, digitisation, management, and dissemination, the project aims to reconstruct the Library’s historical development, with a focus on its preservation efforts, and document the key stages of its growth from its foundation to the 1990s. Analysis of these inventories will shed light on significant events that shaped the Library’s history – such as major acquisitions, losses due to natural events, or collaborations with other institutions – and contribute to a cultural history of science and technology. To facilitate data consultation, the project includes the development of a structured database. Additionally, Optical Character Recognition (OCR) techniques, particularly Handwritten Text Recognition (HTR), will be used for transcription and text search. HTR methods will identify keywords, analyse layouts, and automate author recognition to streamline transcription. This study not only deepens our understanding of the Library’s history and role within its region but also enhances our insights into the evolution of scientific research over time.</div></div>","PeriodicalId":38225,"journal":{"name":"Digital Applications in Archaeology and Cultural Heritage","volume":"39 ","pages":"Article e00459"},"PeriodicalIF":0.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145120482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic inventory of archaeological artifacts based on object detection and classification using deep and transfer learning","authors":"Zied Mnasri ,&nbsp;Andrea D’Andrea","doi":"10.1016/j.daach.2025.e00458","DOIUrl":"10.1016/j.daach.2025.e00458","url":null,"abstract":"<div><div>The inventory of a large collection of archaeological artifacts can be a tedious and time-consuming task. However, nowadays it is possible to reduce its complexity through the use of artificial intelligence tools, including object detection and classification. Deep learning is particularly an AI method which is highly effective for information retrieval and exploration of big datasets. In this work, a technique based on deep learning is applied on an archaeological dataset documenting the discoveries made by the Italian archaeological team at the Al-Baleed site in Oman. The suggested method seeks to: (a) segment photos into individual artifacts; (b) define the segmented artifacts (e.g., pottery, vessel pieces, jewellery, etc.); and (c) categorize the recognized items based on the material used in their handcraft (e.g., earthenware, glass, metal alloy, etc.). Two different kinds of deep neural network models were used to accomplish this twofold function. The first one was used for object identification and was based on Google’s TensorFlow2 Object Detection API, while the second one was created from scratch and trained to categorize the materials of an artifact. An on-site photo collection served as the dataset for training, validating, and testing both varieties of neural nets. However, data augmentation was carried out to provide more training sample versions in order to improve the models’ generalization ability. Evaluation was achieved using standard metrics for each task, such as the mean Average Precision (mAP) for object identification and the overall Accuracy for classification. The findings indicate a good rate of object detection and identification and, more importantly, a satisfactory accuracy of the artifact material’s classification. Besides, benchmarking with state-of-the-art image classification methods, based on transfer learning models, namely SqueezeNet and GoogleNet, which are trained on bigger datasets such as ImageNet, show that the accuracy of the proposed approach attain a comparable accuracy, with the advantage to be specifically trained on the studied dataset. As a result, the models could potentially be used to firstly for creating an automatic inventory process for the archaeological artifacts, and secondly uncover patterns in archaeological data that are currently unknown to assist the identification of items within a sizeable dataset.</div></div>","PeriodicalId":38225,"journal":{"name":"Digital Applications in Archaeology and Cultural Heritage","volume":"39 ","pages":"Article e00458"},"PeriodicalIF":0.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Paperless mapping and cave archaeology. Reviewing BRIC5, SAP6, and mobile device based lidar applications for archaeological cave survey","authors":"Konstantinos P. Trimmis ,&nbsp;Georgios Lazaridis","doi":"10.1016/j.daach.2025.e00463","DOIUrl":"10.1016/j.daach.2025.e00463","url":null,"abstract":"<div><div>Paperless mapping method for cave archaeology executed with the DistoX2 device have been a core methodological application for various archaeological subterranean surveys since 2012. However early in 2020, the production life span of the device that is the backbone to the original method, came to an end with the discontinuation of the Leica x310 base unit and the Bluetooth module. This paper is reviewing other similar instruments for cave survey that follow the same principles with DistoX2 and can replace it in the paperless mapping workflow, while discusses their applicability for cave archaeology. The paper also presents the recently developed Mobile Device Based Lidar sensors and showcases how they can be an alternative way for subterranean archaeological recording.</div></div>","PeriodicalId":38225,"journal":{"name":"Digital Applications in Archaeology and Cultural Heritage","volume":"39 ","pages":"Article e00463"},"PeriodicalIF":0.0,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145159629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Lanna XR dance heritage: Exploring XR for the digitization and transmission of intangible culture","authors":"Kannikar Intawong ,&nbsp;Phimphakan Thongthip ,&nbsp;Songpon Khanchai ,&nbsp;Kitti Puritat","doi":"10.1016/j.daach.2025.e00457","DOIUrl":"10.1016/j.daach.2025.e00457","url":null,"abstract":"<div><div>The preservation of intangible cultural heritage (ICH), particularly traditional dance, faces challenges due to globalization and declining practitioner communities. This study presents the Lanna XR Dance Heritage Project, utilizing Extended Reality (XR) technologies including Virtual Reality (VR), Mixed Reality (MR), and web-based visualization for the digitization and transmission of Lanna Dance, a traditional Northern Thai art form. Through motion capture, the project integrates full-body tracking, smart gloves for hand articulation, and facial expression recognition to ensure cultural fidelity. Twenty-four Lanna Dance forms are categorized into Equipment-Dancing, Without-Equipment Dancing, and Lanna Royal Dancing. Usability and engagement were evaluated with 90 university students across three XR platforms using the System Usability Scale and User Engagement Scale. Findings highlight XR's role in preserving Lanna Dance, offering immersive and interactive experiences that ensure accessibility and cultural sustainability for future generations.</div></div>","PeriodicalId":38225,"journal":{"name":"Digital Applications in Archaeology and Cultural Heritage","volume":"39 ","pages":"Article e00457"},"PeriodicalIF":0.0,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145100256","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrated investigations for diagnosis and restoration of an hypogean mill","authors":"L. De Giorgi,&nbsp;D.F. Barbolla,&nbsp;G. Leucci","doi":"10.1016/j.daach.2025.e00456","DOIUrl":"10.1016/j.daach.2025.e00456","url":null,"abstract":"<div><div>The production of oil in the “Terra d'Otranto” (the current provinces of LE, BR, TA) has accounted for about four centuries, the main economic resource in the province. It happened in “places” known as the presses that have constructive peculiarities, as they derived entirely within the bedrock calcarenitic like “Lecce stone”, “tuff” or “carparo.” They were very popular in the three provinces and are present both in urban centres and on the farms.</div><div>These places, vivid and direct testimony of the rural civilisation, are now at the centre of an extensive work of restoration and enhancement. Given the cultural heritage industry in all respects, the “oil mills” are inserted into the channels of the national roads Olive Oil, Olive Oil Roads named n° 6 and n° 7 (<em>Adriatic and Ionian Antica Terra d'Otranto</em>).</div><div>As with all industrial archaeological heritage, even for the underground presses, the best solution is a conservative reuse. New functions, in this case, are meant to recover the fine in its historical identity as a cultural centre to activate it as a place or be inserted into a circuit in which the museum faithfully reconstructs the ancient “art” of unique production processes. Here, we present the work carried out for the recovery, conservation and enhancement of the underground oil mill located in the centre of Maglie (LE).</div><div>Right from the initial design stage, there was a close relationship between designers, researchers for diagnostics and the representatives of the City of Maglie. After a detailed knowledge of historical material and construction of the hypogeal phenomenon, both a laser scanner and the non-invasive diagnosis by geophysical surveys were performed.</div></div>","PeriodicalId":38225,"journal":{"name":"Digital Applications in Archaeology and Cultural Heritage","volume":"39 ","pages":"Article e00456"},"PeriodicalIF":0.0,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145109667","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"HBIM-HGIS for a multi-level knowledge-based approach","authors":"Rafael Fernandes Dionizio,&nbsp;Eloisa Dezen-Kempter","doi":"10.1016/j.daach.2025.e00461","DOIUrl":"10.1016/j.daach.2025.e00461","url":null,"abstract":"<div><div>Managing heritage assets at an urban scale is a complex task due to the unique characteristics of the buildings and their large scale. Technologies like Historic Building Information Modeling and Historical GIS, combined with digital scanning and 2D data, have emerged to address these challenges. While HBIM and HGIS integration facilitates the extraction and transformation of geometric and semantic information, issues such as data loss during software transfers and the need to adhere to specific standards pose significant challenges. This study focuses on the integration of HBIM and HGIS, using the Pampulha Art Museum as recognized by UNESCO, as a study object. A qualitative exploratory methodology is employed to develop the HBIM-HGIS model and present it via a web-based GIS viewer. The study explores various data integration methods, their advantages, and limitations, contributing to a deeper understanding of HBIM-HGIS integration and offering a foundation for advancing architectural heritage management.</div></div>","PeriodicalId":38225,"journal":{"name":"Digital Applications in Archaeology and Cultural Heritage","volume":"39 ","pages":"Article e00461"},"PeriodicalIF":0.0,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145100255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing creative learning in Thai classical dance education: An integration of digital preservation framework with ubiquitous learning environment","authors":"Napatprapa Pathrapoowanun ,&nbsp;Parama Kwangmuang ,&nbsp;Apirat Siritaratiwat ,&nbsp;Lan Thi Nguyen","doi":"10.1016/j.daach.2025.e00460","DOIUrl":"10.1016/j.daach.2025.e00460","url":null,"abstract":"<div><div>The preservation of Thai classical dance as intangible cultural heritage faces critical challenges in documenting complex movements while maintaining cultural authenticity. Through a three-phase methodology comprising investigation, design, and evaluation, we developed a learning environment model with three key components: Creative Resource Hub for archival documentation, Interactive Studio with movement analysis capabilities, and Collaborative Workshop for preserving teaching methodologies. Testing with 78 secondary school students (39 experimental, 39 control) using cluster random sampling and validated Creative Thinking Assessment Rubric showed significant improvements in creative thinking skills in the experimental group compared to control (mean difference = 6.80, 95 % CI [5.10, 8.50], p &lt; 0.001, Cohen's d = 1.72). The integration of creative development approaches with digital preservation technologies effectively captures both tangible movements and intangible cultural elements while enhancing accessibility through ubiquitous learning features, offering a sustainable model for comprehensive cultural heritage preservation.</div></div>","PeriodicalId":38225,"journal":{"name":"Digital Applications in Archaeology and Cultural Heritage","volume":"39 ","pages":"Article e00460"},"PeriodicalIF":0.0,"publicationDate":"2025-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145100267","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Recognizing past shapes: sex differentiation through deep learning on European Upper Palaeolithic hand stencils","authors":"Verónica Fernández-Navarro ,&nbsp;Aitor González-Marfil ,&nbsp;Ignacio Arganda-Carreras ,&nbsp;Diego Garate","doi":"10.1016/j.daach.2025.e00453","DOIUrl":"10.1016/j.daach.2025.e00453","url":null,"abstract":"<div><div>This study explores the application of advanced deep learning techniques in analyzing Upper Palaeolithic hand stencil representations, focusing on sex classification of individuals involved in prehistoric rock art activity. The research highlights the effectiveness of deep learning models, particularly EfficientNetV2-S, which achieved an accuracy rate of 81.03 % for experimental blown hand stencils and 95.08 % in delineated contemporary hand image samples for sex identification, surpassing traditional morphometric methods. The study demonstrates that deep learning can differentiate male and female hand stencils with high precision, suggesting a mixed-sexual participation in creating prehistoric art, with a slight prevalence of male hand representations in the studied caves. The integration of user-friendly platforms, such as Google Colab, facilitates the reproducibility and validation of these findings, promoting methodological transparency. However, the accuracy of deep learning models is contingent on the quality and preservation of the images, presenting challenges when working with deteriorated or incomplete samples. This work highlights the potential of advanced technologies in archaeological research, opening new avenues for investigating the creation of prehistoric graphic expressions and their social implications.</div></div>","PeriodicalId":38225,"journal":{"name":"Digital Applications in Archaeology and Cultural Heritage","volume":"38 ","pages":"Article e00453"},"PeriodicalIF":0.0,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144890899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"AI tools for generating Digital Heritage Twins enhancing storytelling in educational games","authors":"Nikolaos Kilis,&nbsp;Efstathia Martinopoulou,&nbsp;Giorgos Terzoglou,&nbsp;Efstathios Bozikas,&nbsp;Odysseas Sofikitis,&nbsp;Panagiotis Lepentsiotis,&nbsp;Michael Chatzakis,&nbsp;Nikolaos Dimitriou,&nbsp;Dimitrios Tzovaras","doi":"10.1016/j.daach.2025.e00451","DOIUrl":"10.1016/j.daach.2025.e00451","url":null,"abstract":"<div><div>Digitization of Cultural Heritage (CH) artifacts contributes to the preservation of their historical and societal significance. Their digital counterparts can be widely disseminated through Building Information Modeling applications, historical databases, serious video games, digital educational programs, etc. In this context, we present a (semi-) automated user-friendly framework for 3D asset acquisition, enhancement, and semantic enrichment. These include computer vision modules developed for super-resolution and style transfer on 2D video frames, which are employed to generate 3D assets via multi-view reconstruction. The proposed framework further supports an Active Learning (AL) process that produces images from novel viewing angles inside virtual environments. These views are exploited to improve previously generated 3D assets. 3D content creators can utilize the proposed framework to digitize new or modify and enhance existing assets regardless of size or shape with minor editing from a single video. Several image quality assessment metrics indicate the validity of our methodology.</div></div>","PeriodicalId":38225,"journal":{"name":"Digital Applications in Archaeology and Cultural Heritage","volume":"38 ","pages":"Article e00451"},"PeriodicalIF":0.0,"publicationDate":"2025-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144865222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PyPotteryLens: An open-source deep learning framework for automated digitisation of archaeological pottery documentation","authors":"Lorenzo Cardarelli","doi":"10.1016/j.daach.2025.e00452","DOIUrl":"10.1016/j.daach.2025.e00452","url":null,"abstract":"<div><div>Archaeological pottery documentation and study represents a crucial but time-consuming aspect of archaeology. While recent years have seen advances in digital documentation methods, vast amounts of legacy data remain locked in traditional publications. This paper introduces <em>PyPotteryLens</em>, an open-source framework that leverages deep learning to automate the digitisation and processing of archaeological pottery drawings from published sources. The system combines state-of-the-art computer vision models (YOLO for instance segmentation and EfficientNetV2 for classification) with an intuitive user interface, making advanced digital methods accessible to archaeologists regardless of technical expertise. The framework achieves over 97 % precision and recall in pottery detection and classification tasks, while reducing processing time by up to 5 × to 20 × compared to manual methods. Also, the system's modular architecture facilitates extension to other archaeological materials, while its standardised output format ensures long-term preservation and reusability of digitised data as well as solid basis for training machine learning algorithms.</div></div>","PeriodicalId":38225,"journal":{"name":"Digital Applications in Archaeology and Cultural Heritage","volume":"38 ","pages":"Article e00452"},"PeriodicalIF":0.0,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144865221","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}