Identification of ancient glass artifacts based on FLDA

JiaLin Wan; JianWei Liu; XinXiu Liu; Yong Zhang

doi:10.1117/12.2672533

28 March 2023 Identification of ancient glass artifacts based on FLDA

JiaLin Wan, JianWei Liu, XinXiu Liu, Yong Zhang

Proceedings Volume 12597, Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022); 125973C (2023) https://doi.org/10.1117/12.2672533
Event: Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022), 2022, Nanjing, China

Abstract

Ancient glass artifacts are the physical evidence of cultural exchange between East and West, and their correct identification is significant to archaeological work. However, glass artifacts are highly susceptible to surface weathering caused by the burial environment, which leads to the wrong discrimination of the glass category. In this study, we modeled the weathered artifacts based on Fisher Linear Discriminant Analysis (FLDA), established the index system of the classification model, and obtained the discriminant function for each category of glass artifacts. The correct rate of the model was 98.6% on the test set and 100% on the training set. The results show that the Fisher discriminant model can effectively identify ancient glass types by using the chemical composition indices selected in this study as discriminant factors, which provides a new method for identifying ancient glass artifacts.

Citation Download Citation

JiaLin Wan, JianWei Liu, XinXiu Liu, and Yong Zhang "Identification of ancient glass artifacts based on FLDA", Proc. SPIE 12597, Second International Conference on Statistics, Applied Mathematics, and Computing Science (CSAMCS 2022), 125973C (28 March 2023); https://doi.org/10.1117/12.2672533

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available