Unsupervised Detection and Localization of Egyptian Hieroglyphs
No Thumbnail Available
Date
2024
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
The extensive variability in hieroglyph forms, coupled with erosion, fading, damage, and lighting effects, makes hieroglyphic script highly complex and difficult to segment. This complexity, along with the scarcity of labeled data, poses challenges for traditional supervised learning methods. In this paper, we present a novel unsupervised approach for detecting and localizing Egyptian hieroglyphs in images. Our method employs classical computer vision algorithms to generate pseudo-labels, which are then used to train a Faster R-CNN model. Augmented by post-processing techniques, our approach achieves detection results comparable to that of previous supervised methods for hieroglyph segmentation. Evaluated on unseen backgrounds, it demonstrates significant potential for advancing research in Egyptian culture and history.
Description
CCS Concepts: Computing methodologies → Object detection; Computer vision; Applied computing → Arts and humanities; Archaeology
@inproceedings{10.2312:gch.20241259,
booktitle = {Eurographics Workshop on Graphics and Cultural Heritage},
editor = {Corsini, Massimiliano and Ferdani, Daniele and Kuijper, Arjan and Kutlu, Hasan},
title = {{Unsupervised Detection and Localization of Egyptian Hieroglyphs}},
author = {Lion, Pauline and Trunz, Elena and Klein, Reinhard},
year = {2024},
publisher = {The Eurographics Association},
ISSN = {2312-6124},
ISBN = {978-3-03868-248-6},
DOI = {10.2312/gch.20241259}
}