Ritz, MartinSantos, PedroFellner, Dieter W.Ponchio, FedericoPintus, Ruggero2022-09-262022-09-262022978-3-03868-178-62312-6124https://doi.org/10.2312/gch.20221235https://diglib.eg.org:443/handle/10.2312/gch20221235Manual classification of artefacts is a labor intensive process. Based on 2D images and 3D scans of - for example - ceramic shards, we developed a pattern recognition algorithm which automatically extracts relief features for each newly recorded object and tries to automate the classification process. Based on characteristics found, previously unknown objects are automatically corelated to already classified objects of a collection exhibiting the greatest similarity. As a result, classes of artefacts form iteratively, which ultimately also corresponds to the overall goal which is the automated classification of entire collections. The greatest challenge in developing our software approach was the heterogeneity of reliefs, and in particular the fact that current machine learning approaches were out of question due to the very limited number of objects per class. This led to the implementation of an analytical approach that is capable of performing a classification based on very few artefacts.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies --> Image processing; Applied computing --> ArchaeologyComputing methodologiesImage processingApplied computingArchaeology10.2312/gch.20221235117-1204 pages