Automatic Inspection of Cultural Monuments Using Deep and Tensor-Based Learning on Hyperspectral Imagery

Abstract

In Cultural Heritage, hyperspectral images are commonly used since they provide extended information regarding the optical properties of materials. Thus, the processing of such high-dimensional data becomes challenging from the perspective of machine learning techniques to be applied. In this paper, we propose a Rank-R tensor-based learning model to identify and classify material defects on Cultural Heritage monuments. In contrast to conventional deep learning approaches, the proposed high order tensor-based learning demonstrates greater accuracy and robustness against overfitting. Experimental results on real-world data from UN-ESCO protected areas indicate the superiority of the proposed scheme compared to conventional deep learning models.

Incad: 2d Vector Drawings Creation Using Instance Segmentation

“…Geometric documentation of cultural heritage buildings could be achieved using either conventional or modern photogrammetric approaches in combination with postprocessing steps, providing many products to the users like textured 3D models, orthophotos and 2D architectural vector drawings. There are many researches investigating the use of deep learning techniques on cultural heritage data for 3D documentation (Agrafiotis, Talaveros and Georgopoulos, 2023), and inspection (Tzortzis et al, 2022) among others, using either conventional RGB images or orthophotographies.…”