You are on page 1of 6

EMOTION RECOGNITION IN E-LEARNING SYSTEM

University / Institute Details


Province Sindh City Karachi
University Jinnah University for Campus Karachi
Women
Department Computer Science & Degree Level BS
Software Engineering
Degree Program Software Engineering Telephone (021) 36620857(247)
Fax 3662-0614

Provide Your Supervisor Details


Name Ms. Kanwal Zahoor. Mobile 03343074699

Office Number Email Kanwal.zahoor@juw.edu.pk


(021) 36620857(247)

Designation Lecturer Qualification Masters

Provide Your Head of Department Details


Name Dr. Narmeen Bawany Phone Number
Email narmeen.bawany@juw.edu.pk

Provide Your Project Group Details


Team Lead Team Team Team Team Team Team Team
Member Member Memb Member Member Year Member Member
Name Mobile er Registration of Study Semester CNIC
Email Number
Haleema Sadia 0336-3803492 halimakayani0
YES 2018/COMP/BS( 4 7 4250189687992
93@gmail.com
SE)/22974

NO Tahreem Nazim 0340-0255899 tahreemnazim2 2018/COMP/B 4 7 4220160150172


000@yahoo.co S(SE)/2301
m

Uroobah 0331-2355551 uroobah1998 2018/COMP/B 42101-9151965-6


NO 4 7
Mumtaz @gmail.com S(SE)/23015

2/7
EMOTION RECOGNITION IN E-LEARNING SYSTEM

Provide Your Project Details

Project Title Emotion Recognition In E-Learning System

Project Area of Artificial Intelligence And Deep Learning.


Specialization
Project Start Date 2021-02-05 Project End Date 2022-01-15
Project Summary (less than
Emotion plays an important role for analyzing the student's interest in class room lectures.
2500 characters)
Out of the various ways to detect emotion, the quick way is to understand the emotion
symptoms through facial expression. It is easy to observe the students and their reaction on a
particular topic which is being taught by the instructors. Most of the time in this type of
environment even an important lecture or course ends up with the boredom of the student. All
the effort of the instructor and their instructional aides become ineffective. In order to
overcome these issues,

So we highlight this issue and making a system which will detect student emotion in online
classes or physical classes whether they are paying attention toward the lecture or not,
Observing each student's performance in an intelligent environment, such as facial
expressions, will help teachers dynamically adjust teaching methods by receiving rapid
feedback from this real-time interaction, and will be beneficial to the quality of education
.Firstly we will implement this in e-learning and later implement this in physical class(this
will consider as a future scope)

will help teachers


dynamically adjust teaching methods by receiving rapid feedback from this real-time
interaction, and
will be beneficial to the quality of education
will help teachers
dynamically adjust teaching methods by receiving rapid feedback from this real-time
interaction, and
will be beneficial to the quality of education
will help teachers
dynamically adjust teaching methods by receiving rapid feedback from this real-time
interaction, and
will be beneficial to the quality of education
Our System will detects emotional states of the learners and gives feedback to an instructor
about their instant and weighted emotional states based on facial expressions.
Though facial expressions obviously does not necessarily convey emotions, in computer
vision community,

The term of facial expression recognition often refers to the classification of human facial
features into one of the six basic emotions: happiness, sadness, fear, disgust, surprise and
anger Herein, several classification algorithms were applied to learn instant emotional state
and the best accuracy rates. The Real-time facial emotion recognition is divided into several
phases including detecting general area of human face, this process include tracking system
which require the hardware to monitor the general movement of facial layout, Facial land
marking, which pointing out more accurate facial point to be extracted.

Our focus is on understanding and interpolating the emotional state of the learner during a
learning engagement. Evaluating the emotion of a learner can progressively help in
enhancing learning experience physically and emotionally.
Firstly we will implement this in e-learning and later implement this in physical class(this
will consider as a future scope)

Project Objectives  To Identify emotions of a student


 To automatically identify the type of emotion of the face as happy, anger, disgust,

2/7
EMOTION RECOGNITION IN E-LEARNING SYSTEM

fear, happiness, sadness, and surprise.


 To enable Educator to be aware of the general emotional state of the virtual
classroom.
 To Detect Facial Expressions with Accuracy.
 To make E-Learning and physical classes Interactive.
 To provide a real-time feedback mechanism.

Project Implementation
Method We will be developing a facial expression recognition system based on Python that will
comprise of a website and a mobile application with the aim to integrate it in E-Learning
system that captures and detect the student faces and classify their expressions to make E-
Learning system interactive.

The methodology which is applied to this project is split into three major parts.

The detection phase :This phase consists of the detection of faces, this phase follows two
different steps: The detection of emotions from still or video frames, and the pretreatment to
eliminate the parasites caused by the quality of the optical or electronic devices during the
acquisition of the input image to extract the information essential

The extraction phase: It consists in extracting significant or discriminating information


caused by facial expressions, there are mainly two methods; local methods based on
geometric characteristics and global methods based on appearance, which take the image of
the face as a whole and use well-known statistical analysis techniques.

The classification phase: After extracting all the features of the face region, the
functionalities classification is carried out at the last stage of an automatic facial expression
analysis system. Precisely, this can be done by classifying the characteristics according to the
similarities between the characteristic data, using classifiers such as artificial neural networks
or linear classifiers.

2/7
Emotion Recognition In E-Learning System

Benefits of Project

Direct Beneficiaries of the system:

Most of the time in this type of environment even an important lecture or course
ends up with the boredom of the student. All the effort of the instructor and their
instructional aides become ineffective. In order to overcome these issues, more
interactive learning technologies has been introduced in past few decades but was
not Able to find a better way to analyze the emotions at real-time in an e-learning
environment. Thus there is a necessity or a system to analyze the mood of the
student in an e- learning environment.

So, the instructor will able to know the and have the track of student if they are
getting the interest or not so Direct Beneficiaries is institute and administration will
able know interaction between student and teacher

Outputs from the system:

The system will test different students by showing them a course lecture (video)
where different Results have been observed which is been shown. The different
concentration levels will be observe Throughout the video i.e. high, medium and
low. Thus after analyzing, it is concluded that at some consecutive. Frames the
concentration level is either low/medium/high. Therefore it can be said that the
student was not attentive in reading the content which was displayed at that time
period. So in this administrator can easily get where the lack and try to fulfill the
issues. Experienced instructors can change their teaching style according to

The feedback which they get from their students, subsequently giving extra
attention. Every student could possibly require extra or reduced attention. An e-
learning environment whether online or offline usually contains animated, hyper
texted or text

Industry Linkages:

(School, colleges, universities, institutes, offices and many other who want to know
the participant emotion).
Emotion Recognition In E-Learning System

Technical Details
Of Final Deliverable Hardware Detail:
Our System will use Face detect camera(Logitech Quick cam Sphere AF) to detect
general area of human face emotion and detect general movement of facial movement
in which more accurate facial points will be extracted.

Web Application:
A website will build as a proof of concept. The site will be capable of recognizing
different emotions (neutral, happy, sadness, anger etc) of student. The emotions will
change by time and these emotions change the facial characteristics so the site will
detect the emotions through camera.
Concerning the client-end of the system the functionality is simple enough. At
predefined interval a web camera captures frames from the users while they are
visiting the website. Each captured image is sent to the server for processing. As soon
as the result comes back from the server the interface is changed. On the server-end
the learnt model is loaded from the disk and the web application is ready to process the
images.
The client-side of the website is developed using HTML for the context part of the
page and the Bootstrap framework for CSS styling. The most important component is
the Webcam JS JavaScript library (and open source MIT licensed library) which
provides all the necessary functions for an image to be captured and sent to the server.
It is an AJAX based communication and a callback function accepts the server
response. The JQuery library is used for accessing and altering the Document Object
Model (DOM) of the page. Customizations are i) the bootstrap theme is changed and
b) a different images are shown to the user (each with the recognized emotion). The
server-side part is developed using the Flask framework (BSD licensed) and python as
programming language.

Mobile Application:
An emotion recognition system should be in real time and highly accurate. As a
mobile device has limited processing power, the algorithm in the emotion recognition
system should be implemented using less computation.
Facial image is captured by an embedded camera of a smart phone. Some
representative frames are extracted from the video, and a face detection module is
applied to extract the face regions in the frames. After the face regions are extracted
then it will be capable of recognizing emotions of student.

Final Deliverable of the January 2022


Project
Education Industry
Type of Industry
Deep Face , HTML 5, and JavaScript
Technologies
Sustainable Development
Quality education
Goals
Emotion Recognition In E-Learning System

Provide Your Project Key Milestones

Elapsed time since start of the Milestone Deliverable


project
Requirement gathering Software requirement and specification
Month 1
Document

Month 2 Designing Data modules like Flow diagram,


ERD etc
Prototype for app and web
Month 3 Hardware assembling Data gathering from hardware unit

App development App with two modules


Month 4

Month 5 App completion and integration Remaining modules development and


integration

Web development Website for Emotion Recognition In E-


Month 6
Learning System

Testing System for acceptance testing


Month 7

Month 8 Deployment Whole system integrate on site.

Provide Your Project Equipment Details

Item Name Type No. of Units Per Unit Cost (in Rs) Total (in Rs)
AMD Radeon RX 580 8GB Equipment 1 45000 45000
Graphics card
Logitech Quick Cam Equipment 1 25000 25000
Sphere AF
Miscellaneous 1 10000 10000

Total in (Rs) 70,000


`

You might also like