DeepHadad: Enhancing the Readability of Ancient Northwest Semitic Inscriptions
No Thumbnail Available
Date
2024
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
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.
Description
CCS Concepts: Computing methodologies → Mesh geometry models; Reconstruction; Neural networks; Applied computing → Arts and humanities
@inproceedings{10.2312:gch.20241242,
booktitle = {Eurographics Workshop on Graphics and Cultural Heritage},
editor = {Corsini, Massimiliano and Ferdani, Daniele and Kuijper, Arjan and Kutlu, Hasan},
title = {{DeepHadad: Enhancing the Readability of Ancient Northwest Semitic Inscriptions}},
author = {Aioanei, Andrei C. and Klein, Jonathan and Klein, Konstantin M. and Hunziker-Rodewald, Regine R. and Michels, Dominik L.},
year = {2024},
publisher = {The Eurographics Association},
ISSN = {2312-6124},
ISBN = {978-3-03868-248-6},
DOI = {10.2312/gch.20241242}
}