Towards the Automatic Classification of Pottery Sherds: Two Complementary Approaches

Routledge eBooks, pp. 463–474

Abstract

This paper presents two complementary approaches to automatically classify pottery sherds: one that focuses on the sherd&s;s profile and the other that examines visual features of the sherd&s;s surface. The methods are validated using a set of pottery sherds that were collected during surveys at the ancient site of Koroneia (Greece), which were carried out by the ‘Ancient Cities of Boeotia’ team (under the directorship of Professor J. Bintliff). Both automatic classification techniques produce good results using different sherd classification criteria, such as shape, production technique and chronology.

Authors 9

1. Chiara Piccoli Aachen

   Leiden University

   Affiliation as printed

   Leiden University , The Netherlands

2. Prashant Aparajeya

   Goldsmiths University of London

   Affiliation as printed

   Goldsmiths , University of London , UK

3. Georgios Th. Papadopoulos

   Centre for Research and Technology Hellas

   Affiliation as printed

   Centre for Research & Technology -Hellas , Greece

4. John Bintliff Aachen

   Leiden University

   Affiliation as printed

   Leiden University , The Netherlands

5. Frédéric Fol Leymarie

   Goldsmiths University of London

   Affiliation as printed

   Goldsmiths , University of London , UK

6. Philip Bes

   KU Leuven

   Affiliation as printed

   University of Leuven , Belgium

7. Mark van der Enden

   University of Leicester

   Affiliation as printed

   University of Leicester , UK

8. Jeroen Poblome

   KU Leuven

   Affiliation as printed

   University of Leuven , Belgium

9. Petros Daras

   Centre for Research and Technology Hellas

   Affiliation as printed

   Centre for Research & Technology -Hellas , Greece