Similarity assessment for the analysis of 3D artefacts

Archaeological artefacts are often classified in homogeneous groups, with respect to their origin, use, age, etc., in terms of their physical traits, i.e., colour, material, design pattern, form, shape, size, style, surface texture, technology, thickness, and weight. In particular, when dealing with archaeological exhibits, a single trait is generally not enough for the classification of the artefact because most of the objects are affected by degradation or only partially preserved. In this contribution we propose a shape analysis and comparison pipeline, which combines geometry and texture to identify classes of homogeneous artefacts. The geometric description is based on a statistical technique to select properties that are mutually independent; the photometric information is handled according to a topological perspective, and complemented by the analysis of colour distribution. The outcome is a mixed description of each 3D artefact, which is used to derive a similarity measure between objects. The potential of our method is high since we can include any property representable as real- or vector-valued functions. Experimental results are exhibited to show the efficacy of the method in retrieval and classification tasks.