A Seminar Report

on
“smart emotion detection system using android application”
Submitted by :
Suraj Tupe [Roll No: 53] Sneha Thorat [Roll No: 39]
Snehal Tapare [Roll No: 39]

Under the Guidance of:

Prof.S.S.Pophale

In partial fulfillment of
[B. E. Information Technology]
May-June 2018
At

collegelogo.jpg

Department of Information Technology

Dr.Vithalrao Vikhe Patil College of Engineering, Ahmednagar,
Ahmednagar - 11

Affiliated to

Pune_univ_logo.jpg

SPPU,PUNE
 Dr.Vithalrao Vikhe Patil College of
Engineering, Ahmednagar

CERTIFICATE

This is to certify that the A Seminar Report entitled “smart

emotion detection system using android application” is prepared

by Suraj Tupe,Sneha Thorat,Snehal Tapare of B.E. Information
Technology Engineering, Pune, under the SPPU,Pune and his work is

satisfactory. This work is done during year 2017-18.

Date: ...................................

............................................................

Project Guide [Prof.S.S.Pophale]

............................................................... .........................................................

HOD,Information Technology[Prof.D.A.Vidhate] Project Co-Ordinator [Prof.S.S.Pophale]

Examination:

Internal Examiner :........................................................................

External Examiner :........................................................................

 ACKNOWLEDGMENT

Apart from my own, the success of this report depends largely on the en-
couragement and guidelines of many others. I am especially grateful to my guide
Prof.J.P.Gaidhani who has provided guidance, expertise and encouragement.

I express my heartfelt gratefulness to Prof.D.A.Vidhate, Head of Informa-

tion Technology Department,DVVPCOE, for their stimulating supervision whenever
required during my seminar work. I am also thankful to the staff of Information
Technology Department for their cooperation and support.

I would like to put forward my heartfelt acknowledgement to all my class-

mates, friends and all those who have directly or indirectly provided their over-
whelming support during my seminar work and the development of this report.

Suraj Tupe,Sneha Thorat,Snehal Tapare

 ABSTRACT

The investigation of feelings in human-PC association has expanded in the

new years. With effective order of feelings, we could get moment criticism from
clients, gain better comprehension of the human conduct while utilizing the data
innovations and along these lines make the frameworks and UIs more decided and
clever. In our work, we zeroed in on android application, specifically feelings loca-
tion utilizing looks acknowledgment . Initially, we investigated existing devices that
utilize looks acknowledgment for feeling recognition and analyzed them for a situ-
ation study to get the idea of the best in class. Besides, we proposed a technique
for feeling location utilizing android application that utilizes existing AI draws near.
We assessed it on a standard dataset just as with an investigation, where members
watched feeling summoning music recordings. We utilized Emotiv Epoc to catch
members’ cerebrum movement.
Contents

Contents 1

List of Figures 3

List of Tables 4

1 Introduction of Project Topic 5

1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
1.2 Purpose . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
1.3 Scope . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6

2 Literature Survey 7

3 Proposed System 9
3.1 system Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
3.2 Working . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.3 Algorithm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.4 CNN . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10

4 UML 11
4.1 Usecase . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
4.2 Class . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
4.3 sequence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
4.4 Activity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14

1
 4.5 DFD 0 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
4.6 DFD 1 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15

5 Conclusion 16

Bibliography 17

Appendices 17

2
List of Figures

3
List of Tables

4
Chapter 1

Introduction of Project Topic

1.1 Motivation
Human emotional states play an important role in physiological health and various social
activities such as decision making and communication. Human-computer interaction, for instance,
usually relies on affective computing techniques to detect and model human emotional states and
further improve user experiences with computers [1]. For example, when confusion is detected by
an intelligent tutoring system, the system can improve learning by automatically responding to
individuals with adaptive prompts designed to alleviate their confusion as it was demonstrated by
Zeng et al. [2]. Emotion recognition has also been applied in other real-life scenarios. For example,
studies have shown that stress can negatively influence decision-making abilities [3] and situational
awareness [4], impacting driving capabilities. Picard et al. [5] proposed to detect stress during real-
world driving tasks based on continuously collected physiological signals. Additionally, people’s
emotional responses to advertisements are important to measure their effectiveness. Mcduff et al.
used facial responses to predict ad liking and purchase intent [6]. Since emotional states are closely
related to health, emotion recognition has also been applied to clinical scenarios. For example,
Katsis et al. [7] monitored patients with anxiety disorders during therapeutic sessions based on
physiological signals.

5
1.2 Purpose
Develop an application which is capable of fetching user’s face expression and classify
emotion of user.

1.3 Scope
The objective of the project is detect emotion of user and play music according to the
output. Our prediction system will be useful for user based on the various factors like’s face details
.

6
Chapter 2

Literature Survey

‘1. Detection and Recognition of Human Emotion using Neural Network’

The main aim of our project is to develop a robust system which can detect as well as
recognize human emotion from live feed. There are some emotions which are universal to all human
beings like angry, sad, happy, surprise, fear, disgust and neutral.

Advantage
They implemented system based on Neural network

Disadvantage
They implemented system for desktop

‘2. Overview on emotion recognition system ’

This paper describes the advances made in this field and the various approaches used
for recognition of emotions. The main objective of the paper is to propose real time implementation
of emotion recognition system.

Advantage
Use of ml Method give more accuracy

Disadvantage
They implemented system for desktop

7
‘3. Facial Emotion Detection Using Deep Learning ’

The purpose of this paper is to make a study on recent works on automatic facial emotion
recognition FER via deep learning. We underline on these contributions treated, the architecture
and the databases used and we present the progress made by comparing the proposed methods and
the results obtained. The interest of this paper is to serve and guide researchers by review recent
works and providing insights to make improvements to this field.

Advantage
They developed based on Deep learning

Disadvantage
They implemented system for desktop

‘4. Facial Emotion Detection Using Deep Learning ’

They proposed a method of emotion detection using EEG that employs existing machine
learning approaches. We evaluated it on a standard dataset as well as with an experiment, in which
participants watched emotion-evoking music videos. We used Emotiv Epoc to capture participants’
brain activity. We achieved 53 accuracy in classifying a correct emotion, which is better compared
to 19 accuracy of the existing facial expression based tool Noldus FaceReader

Advantage
They developed based on EEG which give best accuracy

Disadvantage
Using EEG it will take more time

8
Chapter 3

Proposed System

3.1 system Design

9
3.2 Working

We will develop android application to detect and recognize emotional based on face.

We will develop code in android studio using Java language. Our application based on mlkit

to detect emotions

3.3 Algorithm

3.4 CNN

A Convolutional Neural Network (ConvNet/CNN) is a Deep Learning algorithm which can

take in an input image, assign importance (learnable weights and biases) to various as-
pects/objects in the image and be able to differentiate one from the other. The pre-processing
required in a ConvNet is much lower as compared to other classification algorithms. While
in primitive methods filters are hand-engineered, with enough training, ConvNets have the
ability to learn these filters/characteristics. The architecture of a ConvNet is analogous to
that of the connectivity pattern of Neurons in the Human Brain and was inspired by the
organization of the Visual Cortex. Individual neurons respond to stimuli only in a restricted
region of the visual field known as the Receptive Field. A collection of such fields overlap to
cover the entire visual area.

10
11
Chapter 4

UML

4.1 Usecase

12
4.2 Class

4.3 sequence

13
4.4 Activity

14
4.5 DFD 0

4.6 DFD 1

15
Chapter 5

Conclusion

This work demonstrates that accounting for the temporal information of physiological sig-
nals significantly improves the emotion recognition performance; and facial expression and physio-
logical information are complimentary. Furthermore, using proper fusing strategies, we can improve
the accuracy of automatic emotion recognition.

16
Bibliography

1 Vamshi Krishna Gudipati, Oindrila Ray Barman, Mofica Gaffoor, Harshagandha, Abdelshak-
our Abuzneid, Effi- cient Facial Expression Recognition Using Adaboost and Haar Cascade
Classifiers, 2016 IEEE.
2 Ihor Paliy, Face Detection Using Haar - like Fea- tures Cascade and Convolutional Neural
Network, Lviv- Slavsko, Ukraine, TCSET’2008.
3 Anchal Garg, Dr. Rohit Bajaj, Facial expression recog- nition classification using hybridiza-
tion of ICA, GA, and Neural Network for Human-Computer Interaction, Journal of Network
Communications and Emerging Technologies (JNCET), 2015.
4 Namrata Mahajan, Harshad Mahajan, Emotion Detection Algorithm, International Journal
of Electrical and Electronics Research, Vol. 2, Issue 2, pp: (56–60), Month: April - June 2014.
5 Govind U. Kharat, Sanjay V. Dudul, Emotion Recognition from Facial Expression Using
Neural Networks, IEEE 2008.

17