An automated approach for difference detection in cultural heritage applications

Abstract This paper presents the application of two key stages in Cultural Heritage (CH) analysis: cross-time registration and change detection, aimed at automatically identifying subtle geometric variations in CH objects. The proposed method addresses the challenge of manually aligning and detecting differences among large collections of 3D-digitized objects, which is both time-consuming and error-prone. The method combines CrossTimeReg deep learning technique for automatic registration and the Change-Based-Segmentation method for identifying differences and segmented changes. We applied this method to two ceramic sculptures, titled Zephyr and Flora, from the Museum of King Jan III’s Palace at Wilanów, Poland, and validated the results with the CH scientific experts of the museum. The results demonstrated that our method effectively detected geometric variations resulting from potential alterations or restorations, which are crucial for verifying the authenticity of artifacts. Additionally, the method facilitated comparative analysis, enabling researchers to examine similar objects and establish connections, origins, and historical significance. The technique also proved useful in analyzing changes in the geometry of the same object over time due to destructive factors.