Back to main page

DeepHadad: Enhancing the Readability of Ancient Northwest Semitic Inscriptions

Andrei C. Aioanei, Jonathan Klein, Konstantin M. Klein, Regine R. Hunziker-Rodewald, and Dominik L. Michels

Abstract

We present DeepHadad, a novel deep learning approach to improve the readability of severely damaged ancient Northwest Semitic inscriptions. By leveraging concepts of displacement maps and image-to-image translation, DeepHadad effectively recovers text from barely recognizable inscriptions, such as the one on the Hadad statue. A main challenge is the lack of pairs of well-preserved and damaged glyphs as training data since each available glyph instance has a unique shape and is not available in different states of erosion. We overcome this issue by generating synthetic training data through a simulated erosion process, on which we then train a neural network that successfully generalizes to real data. We demonstrate significant improvements in readability and historical authenticity compared to existing methods, opening new avenues for AI-assisted epigraphic analysis.

Paper

In: Eurographics Workshop on Graphics and Cultural Heritage, 2024

Link: https://diglib.eg.org/collections/ab71a152-b620-49fc-a5af-8fed699ef758

Download:

Citation

@Article{Aioanei2024_deep_hadad_short,
	author   = {Aioanei, Andrei C. and Klein, Jonathan and Klein, Konstantin M. and Hunziker-Rodewald, Regine R. and Michels, Dominik L.},
	journal  = {Eurographics Workshop on Graphics and Cultural Heritage},
	title    = {DeepHadad: Enhancing the Readability of Ancient Northwest Semitic Inscriptions},
	year     = {2024},
	month    = {9}
}