Finding on Machine Learning Approaches for Classification of Ancient Ceramics - A Systematic Literature Review

Abstract

Ceramics appraisal is a hot topic in the field of cultural relic collection, dating back to prehistoric times. Traditionally, there are primarily two types of ceramics appraisal methods, which are experience-based methods and technology-based methods. In practice, both methods would cause high costs and be time-consuming. This paper presents the results of a systematic literature review of 22 empirical studies that used machine and deep learning algorithms to classify and identify ancient ceramics, encompassing data collection processes to build datasets, feature extraction of ancient ceramics images, and the selection of machine learning algorithms. Major findings included that there has been a growing number of research projects on the use of machine and deep learning algorithms for the classification of ancient ceramics.