Authors
Marwan Mohamed, Mohamed Yasser, Mohamed Gamal, Abdelrahman Ashraf, Dr. Fatma Helmy, Eng Mahmoud ELSahhar
Publishing Date
20th March 2021
Abstract
The main idea of this project is to study face liveness detection and how can we prevent face spoofing attacks. One of the most widely used biometric approaches is face recognition. Face recognition is used in many Fields. One of these fields is mobile devices authentication. However, face recognition can be easily attacked by a method called face spoofing, That is intended to deceive the face recognition system by facial pictures obtained from images or videos. Other cheaters show the mask of an authorized person to fool the recognition camera into a real person. The proposed system in this document is to use face liveness detection by applying different machine and deep learning algorithms such as CNN, SVM, Naïve bayes, Capsule Neural Network etc. in order to get the best accuracy between them to apply our model. Then, the system will be able to differentiate between live and fake user’s faces.
1.1 Purpose
This Software Design Document (SDD) aims to present a detailed description of project system architecture and design. The document will explain the Face Liveness Detection system features and provide insight into the structure and design of each component. In this document, we shall figure out how this software will be used to achieve a better understanding of the whole system. Also, this document will help the user to have a full overview of the interface and the functions of the project. The system’s main purpose is to detect face spoofing attacks and classify the user’s face input image into live and fake to provide a secured face recognition system.
1.2 Scope
The purpose of this Software Design Document (SDD) is to present detailed description of project system architecture and design. The document will explain the features of the Face Liveness Detection system and provides insight into the structure and design of each component. In this document, we shall figure out how this software will be used to achieve a better understanding of the whole system. Also, this document will help the user to have a full overview about the interface and the functions of the project. The system’s main purpose is to detect face spoofing attacks and classify the user’s face input image into live and fake in order to provide a secured face recognition system.
1.3 Overview
The main goal of the software is to automatically detect the face spoofing attacks and classify the user’s face input image into live or fake. Our aim in this project is to develop a secured and more dependable face recognition system that can be used by any organization. The idea of the system is to take the user’s face as an input image and apply some data pre-processing techniques such as data augmentation, image normalization and feature extraction. Then apply deep learning or machine learning technique to detect if the input image is live or fake. Then the system will view the result to the user and alert the organization if a spoofed image is detected.
1.4 Intended audience
This document is intended for any kind of organization or company that depend on face recognition system in it’s work either using it as attendance system, payment transaction or security access. Those organizations will benefit from our system knowing that no one will gain illegal access in their systems.