Evaluating the Usefulness of Unsupervised monitoring in Cultural Heritage Monuments

TL;DR

This study assesses the effectiveness of six clustering algorithms in monitoring decomposition and corrosion on cultural heritage monuments using hyperspectral imaging, showing some methods achieve accurate deterioration detection.

Contribution

The paper provides a comparative analysis of six clustering techniques applied to hyperspectral images for cultural heritage monitoring, highlighting their effectiveness in detecting deterioration.

Findings

Some clustering methods achieved decent accuracy and precision.

Deterioration detection was quite accurate with certain algorithms.

Evaluation metrics confirmed the suitability of specific clustering approaches.

Abstract

In this paper, we scrutinize the effectiveness of various clustering techniques, investigating their applicability in Cultural Heritage monitoring applications. In the context of this paper, we detect the level of decomposition and corrosion on the walls of Saint Nicholas fort in Rhodes utilizing hyperspectral images. A total of 6 different clustering approaches have been evaluated over a set of 14 different orthorectified hyperspectral images. Experimental setup in this study involves K-means, Spectral, Meanshift, DBSCAN, Birch and Optics algorithms. For each of these techniques we evaluate its performance by the use of performance metrics such as Calinski-Harabasz, Davies-Bouldin indexes and Silhouette value. In this approach, we evaluate the outcomes of the clustering methods by comparing them with a set of annotated images which denotes the ground truth regarding the decomposition and/or corrosion area of the original images. The results depict that a few clustering techniques applied on the given dataset succeeded decent accuracy, precision, recall and f1 scores. Eventually, it was observed that the deterioration was detected quite accurately.