{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:59:50Z","timestamp":1740182390289,"version":"3.37.3"},"reference-count":27,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T00:00:00Z","timestamp":1699228800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T00:00:00Z","timestamp":1699228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>This paper presents a novel approach for fragmented solid object classification exploiting neural networks based on point clouds. This work is the initial step of a project in collaboration with the Institution of \u2018Ente Parco Archeologico del Colosseo\u2019 in Rome, which aims to reconstruct ancient artifacts from their fragments. We built from scratch a synthetic dataset (DS) of fragments of different 3D objects including aging effects. We used this DS to train deep learning models for the task of classifying internal and external fragments. As model architectures, we adopted PointNet and dynamical graph convolutional neural network, which take as input a point cloud representing the spatial geometry of a fragment, and we optimized model performance by adding additional features sensitive to local geometry characteristics. We tested the approach by performing several experiments to check the robustness and generalization capabilities of the models. Finally, we test the models on a real case using a 3D scan of artifacts preserved in different museums, artificially fragmented, obtaining good performance.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad035e","type":"journal-article","created":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T22:46:27Z","timestamp":1697237187000},"page":"045025","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Artificial neural networks exploiting point cloud data for fragmented solid objects classification"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0596-6707","authenticated-orcid":true,"given":"A","family":"Baiocchi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9192-3537","authenticated-orcid":true,"given":"S","family":"Giagu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C","family":"Napoli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6093-8063","authenticated-orcid":true,"given":"M","family":"Serra","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9093-1532","authenticated-orcid":true,"given":"P","family":"Nardelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M","family":"Valleriani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2023,11,6]]},"reference":[{"key":"mlstad035ebib1","first-page":"pp 77","article-title":"PointNet: deep learning on point sets for 3D classification and segmentation","author":"Charles","year":"2017"},{"key":"mlstad035ebib2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","article-title":"Dynamic graph CNN for learning on point clouds","volume":"38","author":"Wang","year":"2019","journal-title":"ACM Trans. Graph."},{"key":"mlstad035ebib3","first-page":"pp 771","article-title":"Color classification of archaeological fragments","volume":"vol 4","author":"Kampel","year":"2000"},{"key":"mlstad035ebib4","first-page":"p 3","article-title":"Archaeological fragment reconstruction using curve-matching","volume":"vol 1","author":"McBride","year":"2003"},{"key":"mlstad035ebib5","first-page":"pp 49","article-title":"Classification of archaeological ceramic fragments using texture and color descriptors","author":"Smith","year":"2010"},{"key":"mlstad035ebib6","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.culher.2012.02.017","article-title":"A flexible approach to reassembling thin artifacts of unknown geometry","volume":"14","author":"Oxholm","year":"2013","journal-title":"J. Cult. Herit."},{"key":"mlstad035ebib7","first-page":"pp 337","article-title":"An efficient technique to recompose archaeological artifacts from fragments","author":"Sanchez-Belenguer","year":"2014"},{"key":"mlstad035ebib8","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1117\/12.2075655","article-title":"3D puzzle reconstruction for archeological fragments","volume":"9393","author":"Jampy","year":"2015","journal-title":"Proc. SPIE"},{"key":"mlstad035ebib9","doi-asserted-by":"publisher","first-page":"847","DOI":"10.3390\/rs11070847","article-title":"Classification of 3D digital heritage","volume":"11","author":"Grilli","year":"2019","journal-title":"J. Remote Sens."},{"key":"mlstad035ebib10","doi-asserted-by":"publisher","first-page":"4086","DOI":"10.1109\/ACCESS.2019.2962791","article-title":"Classification of 3D terracotta warrior fragments based on deep learning and template guidance","volume":"8","author":"Gao","year":"2020","journal-title":"IEEE Access"},{"key":"mlstad035ebib11","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1016\/j.jksuci.2018.09.019","article-title":"Classification and reconstruction algorithms for the archaeological fragments","volume":"32","author":"Rasheed","year":"2020","journal-title":"J. King Saud Univ."},{"article-title":"SRG-Net: unsupervised segmentation for terracotta warrior point cloud with 3D pointwise CNN methods","year":"2020","author":"Hu","key":"mlstad035ebib12"},{"article-title":"Geodesic convolutional neural networks on Riemannian manifolds","year":"2018","author":"Masci","key":"mlstad035ebib13"},{"article-title":"PointCNN: convolution On X-transformed points","year":"2018","author":"Li","key":"mlstad035ebib14"},{"key":"mlstad035ebib15","doi-asserted-by":"crossref","DOI":"10.1145\/3197517.3201301","article-title":"Point convolutional neural networks by extension operators","author":"Atzmon","year":"2018"},{"key":"mlstad035ebib16","first-page":"pp 5425","article-title":"Geometric deep learning on graphs and manifolds using mixture model CNNs","author":"Monti","year":"2017"},{"key":"mlstad035ebib17","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.11","article-title":"Dynamic edge-conditioned filters in convolutional neural networks on graphs","author":"Simonovsky","year":"2017"},{"article-title":"Graph attention networks","year":"2018","author":"Veli\u010dkovi\u0107","key":"mlstad035ebib18"},{"key":"mlstad035ebib19","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00167","article-title":"Revisiting point cloud classification: a new benchmark dataset and classification model on real-world data","author":"Uy","year":"2019"},{"article-title":"Modeling local geometric structure of 3D point clouds using Geo-CNN","year":"2018","author":"Lan","key":"mlstad035ebib20"},{"key":"mlstad035ebib21","first-page":"pp 5560","article-title":"PointWeb: enhancing local neighborhood features for point cloud processing","author":"Zhao","year":"2019"},{"key":"mlstad035ebib22","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/j.neucom.2018.09.075","article-title":"Normalnet: a voxel-based cnn for 3d object classification and retrieval","volume":"323","author":"Wang","year":"2019","journal-title":"Neurocomputing"},{"key":"mlstad035ebib23","first-page":"pp 339","article-title":"Tailored features for semantic segmentation with a DGCNN using free training samples of a colored airborne point cloud","author":"Widyaningrum","year":"2020"},{"key":"mlstad035ebib24","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.3390\/rs12061005","article-title":"Point cloud semantic segmentation using a deep learning framework for cultural heritage","volume":"12","author":"Pierdicca","year":"2020","journal-title":"Remote Sens."},{"article-title":"Open3d: a modern library for 3d data processing","year":"2018","author":"Zhou","key":"mlstad035ebib25"},{"edition":"1st edn","year":"2012","author":"Cantor","key":"mlstad035ebib26"},{"article-title":"DNN and CNN with weighted and multi-task loss functions for audio event detection","year":"2017","author":"Phan","key":"mlstad035ebib27"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad035e","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad035e\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad035e","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad035e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad035e\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad035e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad035e\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad035e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T10:06:02Z","timestamp":1699265162000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad035e"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,6]]},"references-count":27,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,11,6]]},"published-print":{"date-parts":[[2023,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad035e","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2023,11,6]]},"assertion":[{"value":"Artificial neural networks exploiting point cloud data for fragmented solid objects classification","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-06-06","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-10-13","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-11-06","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}