Project Home
PDF access


Ragaa Moustafa, Farida Hesham, Samiha Hussein, Badr Amr

Supervised by: Dr. Taraggy Ghanim, Eng. Nada Ayman, Eng. Samira Refaat

Publishing Date

January 3, 2022


The world’s attention has recently turned towards Ancient Egyptian history. Hence, it has become necessary to have a gadget that translates Hieroglyphs into spoken language. Scriba is a flutter-based mobile application that uses deep learning techniques to identify and translate Hieroglyphic text. Scriba aims to provide people with an accessible and accurate tool to aid them in discovering ancient Egyptian monuments without needing a tour guide.

1.1 Purpose of this document

The motive of this document is to demonstrate a detailed documentation of Scriba’s development process.

1.2 Scope of this document

This document explores systems similar to Scriba, illustrates the overview, scope, and context of Scriba’s system design, and tackles the objectives of the mobile application and the characteristics of its potential users. Furthermore, this document thoroughly explains Scriba’s functional and non-functional requirements, the design limitations, the data design, and the application’s foundational class diagram. Lastly, this document discusses the possible operational scenarios and presents the application’s time plan.

1.3 System Overview

The user will point the phone camera at the hieroglyphs they want to translate. Next, the system will read the scanned image and use data pre-processing techniques to reduce any noise in the photo. Upon finishing the latter, the picture will go through the classification model. Inside the lightweight CNN classifier, the dataset will be read, followed by data pre-processing techniques and feature extraction. Afterward, the data will be split into two sets; training and testing. Cross-validation will then be performed. Lastly, after the hieroglyph is detected, the translation to English or Arabic will appear to the user. The user will be able to listen to the hieroglyphs using the text-to-speech option. And if the scanned hieroglyphs contain a king’s or queen’s name, the user will be asked if they would like to know more about them with the storytelling feature. If the user does not have an internet connection, they can upload an image to the cloud once connected. Upon uploading the picture, the system will recognize the symbols in the photo and translates them.

1.4 System Scope

Scriba aims to help people who are interested in the ancient Egyptian language, such as tourists, students, or tour guides. Therefore, in order to achieve that, the system will contain the following:

1. The hieroglyphs will only be translated to English and Arabic language.

2. Lightweight Convolutional Neural Network architecture will be used in order to make the software more compatible with mobile devices.

3. Being able to recognize not only the hieroglyph, but also the context, since a single hieroglyph can have extended meanings.

4. Users will be able to use a text-to-speech feature if they want to know what the hieroglyphs sound like.