Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
535302 | Pattern Recognition Letters | 2007 | 8 Pages |
Motivated by the requirements of the present archaeology, we are developing an automated system for archaeological classification of ceramics. Classification and reconstruction of archaeological fragments is based on the profile, which is the cross-section of the fragment in the direction of the rotational axis of symmetry. In order to segment the profile into primitives like rim, wall, and base, rules based on human expert knowledge are created. The input data for the estimation of the profile is a set of points produced by the acquisition system. A function fitting this set is constructed and later on processed to find the characteristic points necessary to classify the original fragment. We demonstrate the method and give results on real archaeological data.