Lai, Yu-KunEchavarria, Karina RodriguezSong, RanRosin, Paul L.Sablatnig, Robert and Wimmer, Michael2018-11-112018-11-112018978-3-03868-057-42312-6124https://doi.org/10.2312/gch.20181365https://diglib.eg.org:443/handle/10.2312/gch20181365Heritage monuments such as columns, memorials and buildings are typically carved with a variety of visual features, including figural content, illustrating scenes from battles or historical narratives. Understanding such visual features is of interest to heritage professionals as it can facilitate the study of such monuments and their conservation. However, this visual analysis can be challenging due to the large-scale size, the amount of carvings and difficulty of access to monuments across the world. This paper makes a contribution towards this goal by presenting work-in-progress for developing image-based approaches for detecting visual features in 3D models, in particular of human faces. The motivation for focusing on faces is the prominence of human figures throughout monuments in the world. The methods are tested on a 3D model of a section of the Trajan Column cast at the Victoria and Albert (V&A) Museum in London, UK. The initial results suggest that methods based on machine learning can provide useful tools for heritage professionals to deal with the large-scale challenges presented by such large monuments.Computing methodologiesNeural networksMesh models10.2312/gch.20181365215-219