Detecting Shape Similarities in 3D Pottery Repositories

Shape matching is one of the main research procedures performed by archaeologists. Real time 3D computer graphics, 3D digitisation and content based retrieval are technologies that can facilitate the automation of the shape matching process. As pottery plays a significant role in understanding ancient societies, we focus on the development of compact shape descriptors that can be used for content based retrieval of complete or nearly complete 3D pottery replicas. In this work, we present shape descriptors that exploit the axial symmetry feature and attempt to enhance the archaeological study of pottery by using 3D graphics technologies. We evaluated the performance of the descriptors using a 3D pottery ground truth repository as a test bed. We created an experimental 3D pottery search engine and attempted to integrate a content based retrieval mechanism in a 3D virtual reality environment.