K. L. E.

Society’s
K. L. E. Institute of Technology, Hubballi
Dept of Master of Computer Applications

Project Title : Emotion Recognition

NAME: SAHANA
SINGANNAVAR
USN :2KE21MC039
 CONTENTS

■ INTRODUCTION
■ LITERATURE SURVEY
■ SOFTWARE REQUIREMENTS SPECIFICATIONS
■ DESIGN
■ IMPLEMENTATION
■ SOFTWARE TESTING
■ CONCLUSIONS
Introduction:
When communication is considered, there are three fundamental elements – Words, Tone of Voice
and Non-verbal Behaviour. We have come to look at that non-verbal behaviour, such as facial
expressions which accounts for the biggest section of detecting emotions. Based on psychological
theory, there are a lot of emotions among which few are surprise, fear, disgust, anger, happy and
sad.
Project Description:
■ Recognition of human emotions is a vital phase, which is involved in several applications such
as augmented and virtual reality , advanced driver assistance systems, human computer
interaction, and security systems . Humans have several ways of interpreting the emotions of
others, such as speech and linguistic aspects and facial expressions.
■ Emotion analysis can also be used to track the students emotions to enhance the learning
environment. Therefore, the students can learn better using this approach. Such information
obtained through emotion analysis is useful in monitoring of the overall mood of a group of
persons to identify any destructive events.
■ Computer vision (CV) is the field of study that helps computers to study using different
techniques and methods so that it can capture what exists in an image or a video. There are a
large number of applications of computer vision that are present today like Emotion
Problem Statement
Emotion recognition depicts how the model is trained based on the human facial expressions or
emotions wherein the model gives out different outputs based on webcam capture which uses opencv
library to fetch the human facial expressions .This model can easily identify whether a person is neutral,
happy, sad, surprise, fear, anger, disgust, contempt whenever the facial expression is captured by the
webcam.

Objective
The main objective of our system is emotion recognition has become an important issue in many
application nowadays. In recent years, the research on facial emotion recognition has become
extensive. The aim of facial emotion recognition is to help identify the state of human emotion
(eg; neutral, happy, sad, surprise, fear, anger, disgust, contempt) based on particular facial
images. The challenge on facial emotion recognition is to automatically recognize facial emotion
state with high accuracy. Therefore, it is challenging to find the similarity of the same emotion
state between different person since they may express the same emotion state in various ways.
 LITERATURE SURVEY

Existing System:

In content material mining, identifying human body language is a key issue. Identifying emotion

by seeing is the most ancient style content material depiction and the establishment of unique

states of articulations fashions consisting of Latent Semantic Analysis and point models.
■ Tools and Technologies:
• Python
• Pandas
• TensorFlow
• framework and Libraries
• Visual Studio
• OpenCV
• Numpy
SOFTWARE REQUIREMENT SPECIFICATIONS
A software requirements specification (SRS) is a document that describes what the software will
do and how it will be expected to perform. It also describes the functionality the product needs to
fulfill all stakeholders (business, users) needs.
 System Requirements
Hardware requirements
■ GPU RTX 3090 - 24 GB GRAPHICS
■ RAM 128 GB
■ AMD THREAD RIPPER 3970 X
Software requirements
■ UBUNTU 20.XX
■ PYTHON
■ PYTORCH
■ VS CODE
■ OPENCV FRAMEWORK
Functional Requirement
Functional Requirement defines a function of a software system and how the system must behave when
presented with specific inputs or conditions. These may include calculations, data manipulation and
processing and other specific functionality.
 Anaconda Environment
 Visual Studio
Non-Functional Requirement

 Economical Requirements: Economic feasibility defines whether the expected benefit equals or exceeds the

expected costs. It is also commonly referred to as cost/benefit analysis .

 Technical Requirements:This is about acceptance of the new system by the existing end-users and employees
of the system and author. The website is aiming at employees and now-a-days all of them are aware of web
browsing.

 Usability: Simple is the key here. The system must be simple that people like to use it, but not so complex that
people avoid using it.

 Scalability: The system should be scalable enough to add new functionalities at a later stage. There should be a
common channel, which can accommodate the new functionalities.
DESIGN

The detailed design chapter discusses the various design of the Emotion Recognition , where the
designs start with the use case diagram which depicts the different actors and their functions with the
system.The next diagram is the sequence diagram of the system which is primarily used to show the
interaction between objects in the same order in which each interaction accurs and followed by an
activity diagram of the system where like a flowchart or an activity diagram or data flow diagram
display a succession of evebts or the system’s control flow.These diagrams are frequently used when
modelling business processes.
USE CASE DIAGRAM: Input image

Identifies image

System

Detects Emotion
User

Classifies
Emotions

Displays
Emotion
Data Flow Diagram

Surprise

Input Face
Preprocessing
Feature Smile
Image Extraction

Sad

Classification Anger

Fear

Database Face Preprocessing Feature

Netural
 IMPLEMENTATION
■ PLAN TO BE FOLLOWED
For implementing this project four basic steps are required to be performed:
■ Pre-processing : It is a common name for operations with images at the lowest level of abstraction
both input and output are intensity images.
■ Most pre-processing steps that is implemented are :
■ Reduce the noise
■ Convert the Image to Binary/Grayscale.
■ Pixel Brightness Transformation.
■ Geometric Transformation.
■ Face Registration : Face Registration is a computer technology used in a variety of applications
that identifies human faces in digital images. In this face registration step, faces are first located in
the image using some set of landmark points called “face detection”. These detected faces are then
geometrically normalized to match some template image in a process called “face registration”.
■ Facial Feature Extraction : Facial Features extraction is an important step in face recognition and
is defined as the process of locating specific regions, points, landmarks, or curves/contours in a
given 2-D image. In this feature extraction step, a numerical feature vector is generated from the
resulting registered image. Common features that can be extracted are- a. Lips b. Eyes c. Eyebrows
d. Nose tip .
■ Emotion Classification : In the third step, of classification, the algorithm attempts to classify the
given faces portraying one of the seven basic emotions.
SOFTWARE TESTING
The purpose of testing is to discover errors. Testing is the process of trying to discover every
conceivable fault or weakness in a work product. It provides a way to check the functionality of
components, sub-assemblies, assemblies and/or a finished product it is the process of exercising
software with the intent of ensuring that the Software system meets its requirements and user
expectations and does not fail in an unacceptable manner. There are various types of test. Each test type
addresses a specific testing requirement.

■ System Testing

System Testing is a level of testing that validates the complete software product. The purpose of this
testing is to evaluate all the specifications of the system. In this project, System testing was done by
giving training and testing datasets. This test was done to evaluate whether the system was predicting
accurate results or not.

Unit Testing
■ In unit testing, we designed the whole system in modularized pattern and each module was tested. We
worked on each module until we get accurate outputs.
 Intergration Testing
In integration testing, we combined all the modules which were constructed during the development of the
project. Then the whole system was tested to check whether the prediction given by training dataset to testing
set was accurate or not.

 Alpha Testing

It is the first stage of software engineering which is considered as a actual operational testing done by the
individual member of the project developers group.
CONCLUSION
■ This project proposes an approach for recognizing the category of facial expressions. Our task types the basis
for better human-machine interaction. In its current state, the communication between humans and machines is
very monotone, in general consisting of speech-to-text conversion. By bringing human emotion into the
picture, it’s possible to make the responses of the desktop better.

■ In the future, we would like to add an alarm system that would go off if the application detects that the
individual’s existing emotional country is fatigued/sleepy.
FUTURE ENHANCEMENTS:
■ System is automatic and gives accurate results for instantaneous expressions. It can be used in security systems in

which they can identify the expression of the person. A doctor can use the system to understand the pain of a deaf

patient. This system can also be used to detect what a users state of mind is when they are shopping so that they can try

identifying the feedback of the customers and change some of their marketing ideas and so on.

■ Face expression recognition systems have improved a lot over the past decade. The focus has definitely shifted from

posed expression recognition to spontaneous expression recognition. Promising results can be obtained under face

registration errors, fast processing time, and high correct recognition rate sand significant performance improvements

can be obtained in our system. System is fully automatic and has the capability to work with images feed. It is able to

recognize spontaneous expressions. Our system can be used in Digital Cameras wherein the image can be captured only

when the person smiles. In security systems which can identify a person, in any form of expression he presents himself.

Rooms in homes can set the lights, television to a person’s taste when they enter the room. Doctors can use the system

to understand the intensity of pain or illness of a deaf patient. Our system can be used to detect and track a user’s state

of mind, and in mini-marts, shopping center to view the feedback of the customers to enhance the business etc

■
THANK YOU