You are on page 1of 20

Real-Time Intelligent

Facial Expression
Recognition System
Group Members:
NOOR ALI SHAHBAZ BECS/S15/010
IRFAN ALI BECS/S15/012
M.SULMAN
MAIN FARAZ
Supervisor:
Dr. Sir Farhan Shafiq, HOD
OUTLINE:

 Introduction
 Our Approach
 Hardware Requirements
 Software Requirement
 Block diagram
 Final Deliverables
 Application
 GANTT chart
INTRODUCTION:

 Having a deep understanding of surrounding, one


can predict what is about to happen if he knows
how things behave for a given interaction.
 For living things, it gets difficult to understand them
that what is going to happen or what they are
feeling because we have to judge them intelligently.
 The humans behavior and face expressions tell
many things about them which are heavily
influenced by their emotions.
 In order to understand the surrounding , we have to
understand their emotions.
OUR APPROACH:
 We are designing and developing a system to
recognize the emotions of a person in real time
using Artificial Intelligence techniques.
 We are using Artificial Intelligence Algorithms,
to understand the emotion exhibit by a Person.
HARDWARE AND SOFTWARE
REQUIREMENTS:
The equipment's which we are using in our project are
 Raspberry Pi3
 Arduino UNO
 GSM / WIFI module
 Camera
 LCD
 REST API
 Artificial Intelligence algorithm
 Domain for Central Monitoring Service
 Machine Learning Server
Raspberry Pi 3:

 The Raspberry Pi is a credit-card sized computer which


can be used for many of the things that our desktop PC
does, like word-processing and games.
 It can execute “Python” coded programming.
 It allows us with General Purpose Input Output (GPIO)
pin to create program that can control anything.
Arduino UNO:
 The Arduino Uno is a microcontroller board based on the
ATmega328 .
 It has 14 digital input/output pins - ), 6 analog inputs, a 16
MHz crystal oscillator, a USB connection, a power jack, an
ICSP header and a reset button.
 The Uno differs from all preceding boards in that it does not
use the FTDI usb-to-serial driver chip. Instead, it features the
Atmega8U2 programmed as a usb-to-serial converter.
GSM Module / WIFI Module:

GSM MODULE:
 GSM is a mobile
communication modem; it is stands
for global system for mobile
communication (GSM).
WIFI MODULE:
 It is can give any microcontroller
access to your Wi-Fi network.

A WIFI or GSM module is used to send the data to the server.


REST API:

 It delivers data to and from


devices.
 It is compatible with multiple
platforms.
Machine Learning:

 Machine Learning is the technique of Artificial Intelligence


which enables computers to learn through data and create logic
without explicitly programming them it also enables them to
improve over time as they encounter new data.
Categories of ML:

 Machine learning is classified mainly into three broad


categories.
1. Supervised learning
2. Unsupervised learning
3. Reinforcement learning
In our project , we are applying supervised learning in which,
 The computer is given example inputs and their desired
output.
 The task is to learn the general rule that maps the inputs to
outputs.
Facial Expression Recognition:

 Humans are filled with numerous type of expressions and


emotions. The universal categories for emotions are happy,
sad, surprise, fear, anger, disgust.
 In emotion recognition, good classifier is necessary to
accurately learn the decision boundary.
Emotion Cube:
 The Lövheim cube explains the
relationship between the monoamine
neurotra.
 Eight corners of the cube.
 One advantage of this classification is that
it provides a way to differentiate between
emotions that are not differentiated
according to the arousal and valence
classification such as anger and distress.
Traditional way of Classifying
Emotions:
 Valence represents pleasantness,
happiness versus sadness.
 Arousal represents excitement versus calmness.
TABLE OF EMOTIONS
BLOCK DIAGRAM:

Camera
Raspberry pi REST API
GSM /
WIFI
Database

Trained Emotion
Arduino REST API recognition
Algorithm
SERVER
LCD / Monitor / APP

OUTPUT
FINAL DELIVERABLES:

 Handheld/mounted device for capturing


emotion of the target person in real time.
 Machine Learning for Emotion
Recognition Server.
 A device to display the emotions.
APPLICATIONS:
 Can be used in determining customer satisfaction
 Airport security clearance experience of
passengers
 Interview consultation of the candidate
 Customer experience in audit report of super
markets
GANTT CHART:

Dec 2018 Feb Mar Apr May Jun Jul Aug Sep Oct Nov 2018
Data Collector Module Development
12/8/2017 1/26/2018

Database Management System Design and Development


12/22/2017 1/26/2018

Display Module Development


1/12/2018 1/30/2018

Dataset Development and Preparation of Human Emotions


12/8/2017 3/14/2018

2/9/2018 Designing and Training Artificial Intelligence Model 7/12/2018

Machine Learning Server Development


6/22/2018 8/10/2018

Getting all systems together up and running


8/17/2018 9/6/2018

Developing Web portal and Testing Real time on


Web portal, apps and overall system
9/10/2018 11/9/2018
Thank You

You might also like