Clustering Bayon Face Towers Using Restored 3D Shape Models

Bayon, the well-known Khmer temple at Angkor in Cambodia, is famous for its numerous massive stone face towers. Researchers believe that these facial sculptures can be divided into several meaningful categories. Unlike previous studies, in this paper, each face tower is treated as a basic unit in the classification procedure, as we find that faces located on the same tower have a higher similarity value than those which belong to different ones. 3D replicas acquired by digital scanning are used and a restoration scheme based on the matrix recovery theory is adopted within each tower in order to eliminate the impact of data incompletion. Towers are represented by the average shapes of restored faces and hierarchically clustered based on their similarity values. The spatial distribution of the clustering result shows that there are some patterns among the structure of Bayon, which could be meaningful through further archaeological research.