Translating Egyptian Hieroglyphs using Deep Learning

Umer, Waleed Bin (2024) Translating Egyptian Hieroglyphs using Deep Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Egyptian hieroglyphs that are known for its diverseness has captured the attention of humans for centuries. People working for research or visiting Egypt as tourists are interested equally in knowing more about the insights it holds which is why the tourists are ready to pay high amounts to local guides which helps in translating and understanding. The deep learning models that are used are SSD, YOLOv5, YOLOv8 and Fast R-CNN which identify challenges in Egyptian hieroglyphs and translate them. All these images are curated and pre-processed using different techniques like augmentation, normalization and resizing, all of this is possible via training. All these models are evaluated based on their expertise to function in different systems but they do have the limitations within them. The mean average precision (mAP) of every model varies from backgrounds and in complex situations which determines their capability to work in different settings as mAP of YOLOv8 was 0.975, that outperformed among all models and YOLOv5 also performed well having mAP of 0.970. The Fast R-CNN had mAP of 0.937 and SSD had lowest mAP that is 67.54. This study also explores the technique of optimization within the system for tourists to have seamless reliance on the guides that are local by focusing on the cultural heritage of the Egyptian hierarchy.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Milosavljevic, Vladimir UNSPECIFIED
Subjects:	P Language and Literature > P Philology. Linguistics Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science P Language and Literature > P Philology. Linguistics > Computational linguistics. Natural language processing Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	05 Sep 2025 13:28
Last Modified:	05 Sep 2025 13:28
URI:	https://norma.ncirl.ie/id/eprint/8829

Actions (login required)

View Item