Pottery evolution pattern discovery based on deep learning: case study of Miaozigou culture in China

• Published in: Heritage science Vol. 12; no. 1; pp. 352 - 13
• Main Authors: Pang, Honglin, Qi, Xiujin, Xiao, Chengjun, Xu, Ziying, Ding, Guangchen, Chang, Yi, Yang, Xi, Duan, Tianjing
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 10.10.2024; Springer Nature B.V; SpringerOpen
• Subjects: Algorithms; Artifact identification; Artificial neural networks; Ceramics; Chemistry and Materials Science; Clustering; Culture; Deep Learning; Digital imaging; Evolution; Historic sites; Machine learning; Materials Science; Neural networks; Potteries evolution; Pottery; Clustering; Potteries evolution; Deep Learning

Potteries, one of the tools widely used by early humans, encapsulates rich historical information. Deep neural networks have been applied to analyzing pottery digital images, bypassing the need for intricate handcrafted features. However, existing models focus solely on pottery shape comparison, neg...