Dr. Fatma Helmy
Associate Professor-Computer Science, Misr International University
Teaching Assistant – Computer Science, Misr International University
Monument Recognition in Egypt is a challenging process as it has a wide range of cultures and religions across time. The purpose of this project is to make it easier for tourists to comprehend the stories behind touristic destinations. Many historical places lack information about their enriched past and the battles fought that lead to this monument existing and keeping it standing till our day. The primary goal of this project is to create a virtual tour guide that focuses on recognizing monuments and landmarks in Egypt while also explaining the history and stories behind them. By using traditional and non-traditional machine learning techniques then adding an augmented reality layer to help guide the users. This system has great value because of Egypt’s rich history; millions of people from various nationalities and backgrounds visit Egypt every year to learn more about its beautiful stories.
Our objective is to build an easy to use application, that would help tourists navigate through historical sites in Egypt on their own, without the help or the assistance of any tour guides. So, motivated by the government’s efforts to provide the tourists with the best experience they could have in Egypt, we have decided to create our own application Historia. The application will be able to recognize different monuments with different architecture and will act as a virtual tour guide were it will have an augmented reality layer that will add an explanation about the recognized object.
. Collecting an Egyptian monuments dataset. Also while creating our dataset we will keep in my mind all the criteria of benchmark datasets which are: Relevant, Representative, Non-redundant, scalable ,Reusable. We will create it by using google images and collecting videos and images ourselves
. Recognize monuments and historical places with accuracy higher than 95% based on our deep learning models.
. Recognition for the whole monument even if it is blocked by another object.
. Apply a reliable, fast augmented reality layer to display information with processing speedup to 160 frames/second.
. Detect accurate user’s current location with google maps to find nearby historical places.
. To save the previously visited places in the users history in the database to make the system up to date.
. Provide an easy, user friendly UI to make the system popular among users.
. Offer the information about each monument in multiple languages for usability and under-standing.
. Minimize the processing time since the processing is done on the firestore cloud.
Documents and Presentations
You will find here the documents and presentation for our proposal.
You will find here the documents and presentation for our SRS.
You will find here the documents and presentation for our SDD.
You will find here the documents and presentation for our Thesis
Monuments Recognition using Deep Learning VS Machine Learning