Team Members
Marwan Fathy Mohsen
Team Leader
Khaled Amr Ahmed Adel
Team Member
Karim Ahmed Abdellatif
Team Member
Martina Raafat Kamel
Team Member
Supervisors
Prof. Khaled Moustafa
Professor and vice dean for postgraduate and research of Information and Computer Science college
Eng. Sarah Hatem
Teaching Assistant
Abstract
The chat-bot has attracted the sights of the market need in the past three years. The world faced a pandemic that led everything to be virtualized. Our objective is to create a personalized and interactive 3D avatar by integrating various deep learning models. Users face a significant issue to find a 3D model that can interact with and to record their voice with them. The project aims to simulate a 3D human model. Based on the uploading images from the user. The user can see how the avatar is created and designed by himself in 3D model. Moreover, he will have the ability to generate the avatar by uploading an image that is processed to generate the avatar’s body and face, capturing or uploading an audio recording for cloning the user’s voice. Finally, the user will see his avatar with his own design.
System Objectives
The project Objectives are:
Creating a realistic avatar from the user’s input that relates to the user’s physical, appearance and facial expressions to ensuring that the user have an immersive experience.
Building an advanced NLP model to generate answers and conversation with the user while the user initials a conversation with the avatar.
Developing a customization system to give the ability to the user to customize the avatar appearance, voice, and other features to build an emotional connection between them.
Integrate the TTS to enable the avatar to achieve a conversation with natural and human voice while responding to the user’s questions.
Developing an adaptive learning technology to the avatar for understanding and learning from the user’s preference and communication style and personality by giving the ability to the digital twin to evolve and refine itself.
Develop facial recognition algorithm in order to extract and analyze user’s facial features from image input.
Implementing reinforcement learning algorithms to make the digital human twin adapt on its user, ensuring that at least 65.
Integrate emotional intelligence into the digital twin to recognize and respond to user’se motions.
Integration of image processing techniques to enhance the quality of the user submitted photo.”
System Scope
The system shall make an avatar form anyone just by uploading images turning into 3D model.
The system shall record the voice from the user.
The system shall take an input message from the user.
The system shall create texture from 2d images.
The system shall make a suitable design for the avatar.
The system shall be compatible with different hand-held devices.
Documents and Presentations
Proposal
You will find here the documents and presentation for our proposal.
Document
Presentation
SRS
You will find here the documents and presentation for our SRS.
Document
presentation
SDD
You will find here the documents and presentation for our SDD.
Document
presentation
Thesis
You will find here the documents and presentation for our Thesis
Document
Presentation
Accomplishments
Publications
Competitions
Competition Title
type here detailss about your participation in the competition.