Automatic inspection of cultural monuments using deep and tensor-based learning on hyperspectral imagery
This work addresses the challenge of processing high-dimensional hyperspectral data for cultural heritage inspection, offering a more effective solution for monument preservation.
The paper tackles the problem of identifying and classifying material defects on Cultural Heritage monuments using hyperspectral imagery, achieving greater accuracy and robustness against overfitting compared to conventional deep learning models.
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 UNESCO protected areas indicate the superiority of the proposed scheme compared to conventional deep learning models.