Kareem Yasser, Amr Mohamed, Ahmed Amr, Loay Yehia,  Eng. Samira Refaat, Dr. Fatma Helmy

Publishing Date

9 November 2021


Monument recognition in Egypt is a difficult task due to the country’s many cultures and faiths over time. This initiative aims to make it easier for travelers to understand the backstories of tourist attractions. Many historical sites are devoid of information regarding the monument’s rich past and the fights that led to its creation and preservation to the present day. This project proposes an approach to recognizing monuments using traditional and non-traditional machine learning techniques. For the implementation, three techniques will be tested. Firstly, the ensemble classifier will be tested for the machine learning technique. Secondly, Deep learning classifiers will be tested for the traditional deep learning technique. Finally, the capsule neural network classifier will be implemented for the advanced deep learning technique. Moreover, because of the diversity of animals remaining present in the museums, it is hard to recognize the kind of animal in the Egyptian museum through its bodies; an Augmented Reality layer will be implemented and added to display information about the recognized monuments and to visualize these animals.

1.1 Background

Inspection of historical sites has expanded dramatically as a result of the spectacular expansion of the communication industry. For years, tourism has had a strong effect on many countries, particularly in Western countries. Instead of simply traveling, one might learn about other people and cultures when visiting a certain location. Every day, a large number of tourists from all over the world come to Egypt to explore historical sites. Egypt was selected by 61% of respondents as a country they wished to visit in their lifetime, and Egypt was chosen by 53% as the next great thing in the near future. Unfortunately, many individuals are unable to recognize historical monuments and statues just by looking at it without a caption or a guide. In The Egyptian museum, statues of historical kings and queens can be found such as Thutmosis the third, Hetep, Amenemhat the third, Nefertiti, and others can be found. However, the majority of the present generation of locals, as well as individuals from other nations, lack detailed knowledge of the stories behind these monuments. To improve the tourists’ experience, the project seeks to create an accurate vision system to recognize statues and monuments utilizing traditional and non-traditional machine learning techniques. The goal of putting this idea into production is to include an image or a video and recognize the monuments in it.

1.2 Motivation

From the academic perspective, the work is motivated by 2 reasons. Firstly, working with the capsule neural network. In 2017, the capsule neural network was introduced. Working on a new deep learning system is seen as a significant source of inspiration. A capsule neural network is a sort of artificial neural network that may be used to better simulate hierarchical relationships in a machine learning system. Secondly collecting the dataset. Because there are no datasets for the Egyptian museum monuments published. The dataset will be collected by capturing the monuments there to work with it.

1.3 Problem Statement

The main problem focused on is the monuments detection. The main challenges are the following:

1. Recognition of the statues.

2. Addressing occluded, disoriented, and distorted monuments.

3. Achieving the best accuracy and performance for detection.

4. Augmented reality layer will be implemented for animal visualization and information display.