Classifying fragments of terracotta warriors using template-based partial matching

Large numbers of Terracotta Warriors fragments are mixed up when they are excavated, which calls the need for classifying them in order to avoid one to all matches and improve the efficiency of reassembly. In this paper, we propose a novel template-based classification algorithm for Terracotta Warriors fragments, which transforms the problem of classification into the problem of partial shape matching. Firstly, a few distinct regions, which indicate categories of the fragments, are selected as templates from collections of fragments. Secondly, a novel partial matching procedure is proposed to find whether a fragment have a sub-region that is similar to one of the templates. If there exists a sub-region on the fragment that is similar to one of the templates, this fragment is considered to belong to the category that the matching template represents. The partial matching procedure consists of a coarse matching and a fine matching, which utilizes the normal distribution descriptor and the modified point feature histogram descriptor, respectively. The normal distribution descriptor characterizes the structure of a Euclidean-sphere region and the modified point feature histogram descriptor characterizes the structure of a geodesic-disk region. Experiments have been conducted on Terracotta Warriors fragments that are scanned from real sites to verify the effectiveness of our method. Comparing with other partial matching methods, more accurate classification results are achieved.