项目作者: driouecheMed

项目描述 :
Face recognition using FaceNet, and for security we add eye blinking detection for detecting fake faces.
高级语言: Jupyter Notebook
项目地址: git://github.com/driouecheMed/Face-Recognition.git
创建时间: 2020-05-19T15:10:17Z
项目社区:https://github.com/driouecheMed/Face-Recognition

开源协议:

下载


Face-Recognition

This project is composed to 3 parts:

  • FaceNet a face recognition system.
  • Liveliness Net a a security system for face recognition.
  • Real Time Implementation a real time face recognition system.

FaceNet

FaceNet learns a neural network that encodes a face image into a vector of 128 numbers.
By comparing two such vectors, you can then determine if two pictures are of the same person.

Encoding model : Inception

Loss: Triplet loss

Liveliness Net

Face recognition systems can be circumvented simply by holding up a photo of a person to the face recognition camera.
In order to make face recognition systems more secure, we need to be able to detect such fake/non-real faces using Liveliness Net.

Problem: Binary classification of eye status.

Dataset : Closed Eyes In The Wild (CEW) dataset

Model : LeNet-5

Real Time Implementation

Combine the two previous networks, and implementing real time feature using opencv.

Idea : We won’t confirm the face if it’s detected until the eyes blink.

Face detection task : openCV pre-trained Haar-cascade classifier.