Classification of ceramic fabrics has long held a major role in archaeological pursuits. It helps answer research questions related to ceramic technology, provenance, and exchange and provides an overall deeper understanding of the ceramic material at hand. One of the most effective means of classification is through petrographic thin section analysis. However, ceramic petrography is a difficult and often tedious task that requires direct observation and sorting by domain experts. In this paper, a deep learning model is built to automatically recognize and classify ceramic fabrics, which expedites the process of classification and lessens the requirements on experts. The samples consist of images of petrographic thin sections under cross-polarized light originating from the Cocal-period (AD 1000-1525) archaeological site of Guadalupe on the northeast coast of Honduras. Two convolutional neural networks (CNNs), VGG19 and ResNet50, are compared against each other using two approaches to partitioning training, validation, and testing data. The technique employs a standard transfer learning process whereby the bottom layers of the CNNs are pre-trained on the ImageNet dataset and frozen, while a single pooling layer and three dense layers are added to 'tune' the model to the thin section dataset. After selecting fabric groups with at least three example sherds each, the technique can classify thin section images into one of five fabric groups with over 93% accuracy in each of four tests. The current results indicate that deep learning with CNNs is a highly accessible and effective method for classifying ceramic fabrics based on images of petrographic thin sections and that it can likely be applied on a larger scale.
Archaeologists are interested in better understanding matters of our human past based on material culture. The tools we use to approach archaeological research questions range from the trowel and brush to, more recently, even those of artificial intelligence. As access to computing technology has increased over time, the breadth of computer-assisted methods in archaeology has also increased. This proliferation has provided us a considerable toolset towards engaging both new and long-standing questions, especially as interdisciplinary collaboration between archaeologists, computer scientists, and engineers continues to grow. As an example of an archaeological project engaging in computer-based approaches, the Guadalupe/Colón Archaeological Project is presented as a case study. Project applications and methodologies range from the regional-scale identification of sites using a geographic information system (GIS) or light detection and ranging (LiDAR) down to the microscopic scale of classifying ceramic materials with convolutional neural networks. Methods relating to the 3D modeling of sites, features, and artifacts and the benefits therein are also explored. In this paper, an overview of the methods used by the project is covered, which includes 1) predictive modeling using a GIS slope analysis for the identification of possible site locations, 2) structure from motion (SfM) drone imagery for site mapping and characterization, 3) airborne LiDAR for site identification, mapping, and characterization, 4) 3D modeling of stone features for improved visualization, 5) 3D modeling of ceramic artifacts for more efficient documentation, and 6) the application of deep learning for automated classification of ceramic materials in thin section. These approaches are discussed and critically considered with the understanding that interdisciplinary cooperation between domain experts in engineering, computer science, and archaeology is an important means of improving and expanding upon digital methodologies in archaeology as a whole.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.