• Corpus ID: 18253471

Automatic Classification of Archaeological Potsherds

  title={Automatic Classification of Archaeological Potsherds},
  author={Chaouki Maiza and V{\'e}ronique Gaildrat},
During archaeological excavations, one of the most time consuming stages is the treatment of the great number of pottery sherds found on the site (labelling, drawing, measuring and classifying as related to the known object models). This step is also the most difficult one because it requires an extended knowledge of the characteristics of the already identified object models that can be found on a given archaeological site. As digitalization techniques have become financially reachable, new… 

Figures and Tables from this paper

SemanticArchaeo : A Symbolic Approach of Pottery Classification

The complete objects database is organized in a different way than the archaeologists’ classical style so as to facilitate the treatment of the potsherds and can achieve matching using first the symbolic description and in a second way the exact geometry of the objects.

A Survey of Computer Methods in Reconstruction of 3D Archaeological Pottery Objects

Manuscript History: An automatic reconstruction of ancient artifact fragments is of great interest in archaeology, and is considered important because it helps archaeologists make inferences about

A 3D Informational Database for Automatic Archiving of Archaeological Pottery Finds

A dedicated database has been proposed, able to store the information extracted from huge quantities of archaeological material using a specific shape feature recognizer, and implemented and used for the identification of pottery fragments and the reconstruction of archaeological vessels.

Automatic Shape Feature Recognition for Ceramic Finds

The proposed method performs a shape feature segmentation of the sherds, which is fundamental to undertake any further analysis, such as potsherds classification, reconstruction, or cataloging, and its performance is tested in the analysis of some real, critical cases.

Review of computer-based methods for archaeological ceramic sherds reconstruction

A comprehensive analysis of the most important available publications until the end of 2019 is presented, and state-of-the-art computer-based methods for archaeological ceramic sherds reconstruction are reviewed, and some recommendations for future researches are proposed.

A computer tool to identify best matches for pottery fragments

KETCH : Automatic 3 D Representation of Pottery from Paper Catalogue Drawings

The pipeline includes methods for understanding a 2D drawing and using it for constructing a 3D model of the pottery and methods for capturing images of these sherds in a way that matches the imaging methodology of archaeologists.

Categorization of Aztec Potsherds Using 3D Local Descriptors

The Tepalcatl project, an ongoing bi-disciplinary effort conducted by archaeologists and computer vision researchers, which focuses on developing statistical methods for the automatic categorization of potsherds from ancient Mexico including the Teotihuacan and Aztec civilizations, is introduced.

Computer Applications in Archaeological Pottery: A Review and New Perspectives

During the past few years, many publications about computer applications in the field of drawing, classification and analysis of archaeological pottery have been presented at various congresses by

VASESKETCH : Automatic 3 D Representation of Pottery from Paper Catolog Drawings

The pipeline includes methods for understanding a 2D drawing and using it for constructing a 3D model of the pottery and methods for capturing images of these sherds in a way that matches the imaging methodology of archaeologists.



3D Reconstruction of Archaeological Pottery using Profile Primitives

In this work a bottom up design using a description language is the basis for the automatic classification and reconstruction of newly found fragments of unknown type.

An Automatic Estimation Of The Axis Of Rotation Of Fragments Of Archaeological Pottery: A Multi-Step

This paper presents a method for an estimation of the axis of r otation of radially symmetric objects from their fragments. In particular, fragments of archaeologic al pottery are considered. The

Using Geometric Modeling for Archiving and Searching 3D Archaeological Vessels

This paper presents a method for archiving and searching 3D Native American ceramic vessels using geometric modeling techniques, which includes modeling the data with parametric surfaces, extracting features to raise the level of abstraction of data, and organizing vessel data based on XML schema.

Advances in geometric modeling and feature extraction on pots

A bstract: This paper outlines progress on the 3D Knowledge and Distributed Intelligence project (3DK) at A rizona State University. Three of the six 3 DK pilot projects involve archaeological and

Geometric Structure Estimation of Axially Symmetric Pots from Small Fragments

The recovery of geometric structure from noisy data poses difficult non-linear statistical estimation problems. This paper describes a novel, robust, low computational cost approach for finding the

Accurately Estimating Sherd 3D Surface Geometry with Application to Pot Reconstruction

This paper discusses an automatic method for accurately estimating an axis/profile curve pair for each archeological sherd (even when they are small) based on axially symmetric implicit polynomial surface models and briefly discusses how the estimation results may be integrated into a larger pot reconstruction program.

On the Interactive 3D Reconstruction of Iberian Vessels

This algorithm has been implemented within a reconstruction application that has been successfully used to reconstruct Iberian pottery and it accomplishes three tasks in a semi-automatic way: orientation of the sherd, computing the symmetry axis and detecting the profile.

Bayesian assembly of 3D axially symmetric shapes from fragments

  • A. WillisD. Cooper
  • Computer Science
    Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
  • 2004
The system represents at least three significant advances over previous 3D puzzle solving approaches : a Bayesian framework which allows for easily combining diverse types of information extracted from each sherd, a search which reduces comparisons on unlikely configurations, and a robust computationally reasonable method for aligning break curves and sherd outer surfaces simultaneously.

Morphological Analysis of Shapes

A multiresolutional discretization scheme for the boundary of a planar connected shape, by means of the Haar wavelet transform, and an eecient, adaptive algorithm based on the Constrained Delaunay Triangulation of polygons for skeletonizing the shape are described.

Alignment of multiple non-overlapping axially symmetric 3D datasets

  • A. WillisD. Cooper
  • Mathematics
    Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.
  • 2004
A stochastic method for automatically estimating the unknown axially-symmetric global surface and break-curves is proposed which solves an application of interest, specifically the reconstruction of archaeological pots from subsets of their surface pieces.