Uncover Common Facial Expressions in Terracotta Warriors: A Deep Learning Approach

TL;DR

This paper applies deep learning and GANs to analyze and identify common facial expressions in Terracotta Warriors, overcoming data scarcity and feature differences to enhance art research and ancient art understanding.

Contribution

It introduces a novel application of deep learning and GAN-generated data to analyze facial expressions of Terracotta Warriors, a previously unexplored area.

Findings

GANs effectively generate high-quality facial expression data

Deep learning models identify common expressions in Terracotta Warriors

Method provides new insights for art and cultural research

Abstract

Can advanced deep learning technologies be applied to analyze some ancient humanistic arts? Can deep learning technologies be directly applied to special scenes such as facial expression analysis of Terracotta Warriors? The big challenging is that the facial features of the Terracotta Warriors are very different from today's people. We found that it is very poor to directly use the models that have been trained on other classic facial expression datasets to analyze the facial expressions of the Terracotta Warriors. At the same time, the lack of public high-quality facial expression data of the Terracotta Warriors also limits the use of deep learning technologies. Therefore, we firstly use Generative Adversarial Networks (GANs) to generate enough high-quality facial expression data for subsequent training and recognition. We also verify the effectiveness of this approach. For the first time, this paper uses deep learning technologies to find common facial expressions of general and postured Terracotta Warriors. These results will provide an updated technical means for the research of art of the Terracotta Warriors and shine lights on the research of other ancient arts.