Computer Science and Engineering, Department of
Date of this Version
6-2018
Citation
Shruti Daggumati and Peter Z. Revesz. 2018. Data Mining Ancient Script Image Data Using Convolutional Neural Networks. In Proceedings of 22nd International Database Engineering & Applications Symposium, Villa San Giovanni, Italy, June 18–20, 2018 (IDEAS 2018), 6 pages. https://doi.org/10.1145/3216122.3216163
Abstract
The recent surge in ancient scripts has resulted in huge image libraries of ancient texts. Data mining of the collected images enables the study of the evolution of these ancient scripts. In particular, the origin of the Indus Valley script is highly debated. We use convolutional neural networks to test which Phoenician alphabet letters and Brahmi symbols are closest to the Indus Valley script symbols. Surprisingly, our analysis shows that overall the Phoenician alphabet is much closer than the Brahmi script to the Indus Valley script symbols.
Included in
Computer Engineering Commons, Digital Humanities Commons, Electrical and Computer Engineering Commons, History of Art, Architecture, and Archaeology Commons, Near Eastern Languages and Societies Commons, Other Classics Commons, Other Computer Sciences Commons, South and Southeast Asian Languages and Societies Commons
Comments
© 2018 Copyright held by the authors. Licensed CC-BY-NC-SA.