DESIGN AND

TECHNOLOGY(DT)

PROJECT LOGBOOK

PROJECT NAME: Emotion recognition with Machine Learning

SCHOOL NAME: Kendriya Vidyalaya Kanchanbagh Hyderabad

YEAR/CLASS: 2025-26/XII

TEACHER NAME: Mr. Anil Kumar

TEACHER EMAIL: anilkumarpgtcs@[Link]

TEAM MEMBER NAMES AND GRADES:

1. PRIYANSHU KUMAR (XIIA)

2. SHREEKA JOSHI (XIIA)

3. SHRUTI SINGH (XIIA)

4. [Link] REDDY (XII A)

5. [Link] BAITHARU (XII A)

INTRODUCTION
This document is our Project Logbook, and it is where we recorded our ideas, thoughts and
answers as we worked to solve a local problem using AI.

We Made a copy of the document in our shared drive and worked through it digitally with
our team. we also printed a copy of the document and submitted a scanned copy once we
had completed the Project Logbook. All the members who worked in this project Felt free to
add pages and any other supporting material to this document.

TEAM ROLES
1.1 Who was in our team and what were their roles?

ROLE Role description Team Member Name

Project Leader Scheduled the task among the team members, PRIYANSHU KUMAR
ensures the task is completed on time. And
maintained a productive and friendly work
environment

Data Expert Decided upon the data required and the type of SHREEKA JOSHI
data for training the model, collected the data,
ensured the type of data and its authenticity.

Information Collected questions from the end users that SHRUTI SINGH
Researcher needed to be answered, looked for the answers
to those questions and then prepared a report
that was passed to the project leader.

Designer Created the design and the flow of how to go [Link] BAITHARU
about making the solution for the problem
statement.

Prototype Worked to build the model, train it followed by PRIYANSHU KUMAR

Builder/Coder/Teste testing the efficiency and accuracy of the model.
r [Link] REDDY
 1.2 Project plan
The following table is a guide for our project plan. we used this to create our own version
using a spreadsheet which we pasted into this section. we expanded the ‘Notes’ section to
add reminders, things that we needed to follow up on, problems that needed to be fixed
urgently, etc.

Phase Task Planned Planned Planned Actual Actual Actual Who is Notes/Remarks
start end duratio start end date duration responsible
date date n date (hours,
(hours, minutes)
minutes)
Coursework, 7/11/2025 5/12/2025 4-5 hours 7/11/2025 10/12/2025 20-30 hours All team BTech courses
readings
members
Preparing for
the project
Set up a 07/11/2025 07/11/2025 30 minutes 05/11/2025 07/11/2025 45 minutes Shruti Singh
team folder
on a shared
drive
08/11/2025 08/11/2025 2 hours 08/11/2025 08/11/2025 2 hours All team
members
Background
Defining reading
the problem
08/11/2025 09/11/2025 2 hours 08/11/2025 09/11/2025 2 hours All team
Research members
issues in our
community

Team meeting 08/11/2025 09/11/2025 2 hours 08/11/2025 09/11/2025 2 hours All team Collaborative Work
to discuss members
issues and
select an issue
for the project

09/11/2025 10/11/2025 2 hours 09/11/2025 10/11/2025 2 hours

Complete Shreeka
section 3 of
the project
logbook

4/5
Rate
yourselves
09/11/2025 09/11/2025 1 hour 09/11/2025 09/11/2025 1 hour All team
Identify users members

Understanding
the users
10/11/2025 10/11/2025 2 hours 10/11/2025 10/11/2025 2 hours 30 All team
Meeting with Morning Morning minutes members
users to

observe them

10/11/2025 10/11/2025 1 hour 10/11/2025 10/11/2025 1 hour All team

Interview Morning Morning Morning Morning members
with user (1)
Interview 10/11/2025 10/11/2025 1 hour 10/11/2025 10/11/2025 1 hour All team Online Interactions
with user (2), Afternoon Afternoon Afternoon Afternoon members with end users
etc…
Complete 10/11/2025 13/11/2025 2 hours 11/11/2025 14/11/2025 2 hours Collaborative Work
section 4 of Priyanshu
the Project
Logbook
 Rate 4/5
Yourselves

16/11/2025 16/11/2025 4 hours 16/11/2025 16/11/2025 6 hours All team Online Interactions
Team meeting Morning Afternoon Morning Afternoon members with end users
Brainstorming to generate
ideas for a
solution

Complete 16/11/2025 17/11/2025 3 hours 16/11/2025 19/11/2025 3 hours All team Collaborative Work
section 5 of members
the Project
Logbook
Rate 4/5
yourselves
Team 20/11/2025 21/11/2025 6 hours 20/11/2025 21/11/2025 All team Online Meeting
members

Designing
meeting to
your solution
design the
solution
Complete 21/11/2025 22/11/2025 4 hours 21/11/2025 23/11/2025 5 Hours Shruti, Roshan Online Meeting
section 6 of
the logbook
Rate
yourselves
Collecting Team 24/11/2025 25/11/2025 4 hours 24/11/2025 25/11/2025 4 hours All team Various online
and meeting to members meetings with
preparing discuss data counsellor & teacher
requirements
data
Data 26/11/2025 26/11/2025 1 hour 26/11/2025 26/11/2025 2 hours Shreeka
collection
Data 27/11/2025 27/11/2025 2 hours 28/11/2025 28/11/2025 3 hours Shruti
preparation
Collecting and labelling
and
preparing Complete 29/11/2025 30/11/2025 4 hours 30/11/2025 31/11/2025 4 hours Vinayak
Section 6 of
data the Project
Prototyping Logbook
Team 31/11/2025 31//11/2025 3 hours 31/11/2025 31//11/2025 5 hours All team Collaborative Work
meeting to members
plan
prototyping
phase
Train your 01/12/2025 01/12/2025 2 hours 01/12/2025 01/12/2025 2 hours Priyanshu
model with
input dataset
Test your 01/12/2025 01/12/2025 1 hour 01/12/2025 01/12/2025 1 hour Shreeka
model and
keep training
with more
data until you
think your
model is
accurate
Write a 02/12/2025 02/12/2025 1 hour 01/12/2025 02/12/2025 1 hour Roshan
program to
Prototyping initiate
Testing actions
based on the
result of your
model
Complete 03/12/2025 04/12/2025 4 hours 03/12/2025 04/12/2025 3 hours Vinayak
section 8 of
the Project
Logbook
Rate 5/5
yourselves
Team 05/12/2025 05/12/2025 4 hours 05/12/2025 05/12/2025 5 hours All team Collaborative Work
meeting to members
discuss
testing plan
Completing Reflect on 07/12/2025 07/12/2025 2 hours 07/12/2025 07/12/2025 2 hours All team Collaborative Work
the logbook the project members
with your
team
Complete 08/12/2025 09/12/2025 4 hours 08/12/2025 09/12/2025 5 hours Priyanshu Online meeting
sections 10
Shreeka
and 11 of the
Project Roshan
Logbook
Review your 09/12/2025 09/12/2025 1 hour 09/12/2025 09/12/2025 1 hour Vinayak
Project
logbook

Submit your 09/12/2025 09/12/2025 1 hour 09/12/2025 1 hour Shruti

Submission entries on
the IBM
 1.3 Communications plan

Did we meet face-to-face, online or a mixture of each to communicate? Offline

How often did we come together to share our progress? Thrice a week

Who set up online documents and ensured that everyone is contributing? All the members

What tools did we use for communication? Microsoft Teams, WhatsApp, Google Drive and

Google Docs for collaborative documentations and work

 2.4 Team meeting minutes

MEETING-01

Date of meeting:08-11-2025
Who attended: All members
Who wasn’t able to attend: NA
Purpose of meeting: Discussion about the project, Assigning duties
Items discussed:
[Link] goals
[Link] discussion about the Topic
[Link] duties

Things to do (what, by whom, by when)

[Link] changes and improvements in the project- Shruti, Roshan
[Link] data- Shruti Singh
[Link]-Priyanshu,Vinayak
[Link]- Shreeka

MEETING-02
Date of meeting:10-11-2025
Who attended: All members
Who wasn’t able to attend: NA

Purpose of meeting: Discussion on the data requirements.

Items discussed:
[Link] of data needed
[Link] of data
[Link] to process data

Things to do (what, by whom, by when):

[Link] the data-Shreeka
[Link] -Roshan
[Link] the solution-Vinayak
[Link] completion
 MEETING-03
Date of meeting:16-11-2024
Who attended:All Members
Who wasn’t able to attend:NA

Purpose of meeting:Designing the solution

Items discussed:
[Link]
[Link] up with different ideas for designing the solution for users
[Link] the analytical approach to be taken

Things to do (what, by whom, when):

[Link] of intent, nodes, and entities
[Link] completion till brainstorming.
[Link] of coding and designing the user interface-Somesh,Sourav

MEETING-04
Date of meeting:20-11-2024
Who attended:All members
Who wasn’t able to attend:NA

Purpose of meeting:Discuss the testing plan, and testing the model

Items discussed:
[Link] plan for better precision
[Link] any improvements or enhancement.
[Link] for final presentation

Things to do (what, by whom, when):

[Link] the model for analyzing the accuracy and efficiency of the model-All team members
[Link] changes or improvements to be made-Somesh
[Link] by the users
[Link] of final presentation before 1 week of the deadline of project submission

MEETING-05
Date of meeting: 23-11-2025
Who attended: All members
Who wasn’t able to attend: NA

Purpose of meeting: Gathering user feedback, Final presentation plan

Items discussed:
[Link] on the final presentation and evaluating the team’s performance
[Link] feedback form team members and users
[Link] areas of improvement and what could have been done differently

Things to do (what, by whom, when):

[Link] user feedback- Shounak, Soumya
[Link] to be done as per testing by the users- Shree, Sourav
[Link] individual reflections and experiences

MEETING-06

Date of meeting:10-12-2025
Who attended: All the members
Who wasn’t able to attend: NA

Purpose of meeting: Project Closure and Video Filming

Items discussed:
[Link] the project closure report
[Link] recording software to be used
[Link] the entities, dialogs to include in the video

Things to do (what, by whom, when):

[Link] of presentation of slides- Somesh
[Link] writing- Sourav, Somesh
[Link] the video- Sourav
[Link] the final presentation

PROBLEM DEFINITION
1.4 Important local issues faced by the customers
 ● Due to increased prices of new cars, customers are financially incapable of buying it.

● Customers have very little knowledge about the features and are incapable in deciding the
worthiness of cars according to their respective selling price.

● It is also very time consuming for the users on estimating the car’s value based on it’s
features.

● The seller also has no idea about the car’s existing value or the price he should be selling the
car.
Because of these, used car sales are on a global increase.

1.5 Which issues mattered to us and why?

The following are the major concerns for us faced by the users
● The increased prices of new cars and the financial incapability of the customers to buy them.
● The seller also has no idea about the car’s existing value or the price he should be selling
the [Link] the seller decides a price randomly and the buyer has no idea about the car
and its value.
● Buyers have no idea about the price and features of new cars in the industry .

1.6 Which issue Did we focus on?

● Our focus was on resolving every issue related to the cars e.g-budget, fuel efficiency, safety
features, reliability, warranty, personal preferences etc.
● The focus was also on reducing time consuming processes and delayed responses.
 1.7 Our team’s problem statement is in the format below.

How did we help the customers find a way to give users an accurate estimate of how much had
to be paid for a given vehicle so that they could save time and have the sufficient data to help
them in finding the desired car for them.

Rate yourself: 3

Problem Definition

1 point - A local problem is described

2 points - A local problem which has not been fully solved before it is described.
3 points - A local problem which has not been fully solved before it is explained in detail with supporting research.
THE USERS
1.8 Who were the users and how were they affected by the problem?

* Buyers/Customers
Sellers

* the buyer has no idea about the car and its value in the present- day scenario.
In fact the seller also has no idea about the car’s existing value or the price he/she should be
selling the car.

1.9 What have we actually observed about the users and how the problem
affected them?

● Customers while buying a car, users are facing confusion regarding the budget, quality ,
features etc.

● When this situation arises it gets more difficult to choose a specific product.

● Securing financing can be challenging,especially for buyers with poor credit.

● Sellers may price their cars too high based on emotional attachment or lack of market
knowledge,leading buyers to overpay.
 1.10 Our interview questions here as well as responses from users.

Q1. Is it your first time buying a car?

Ans. Yes, it’s my first experience.

Q2. What features does your current vehicle have that you’d like to see in a new vehicle?
Ans. Proper mileage, durable, more pickup power

Q3. Are you looking for something immediately or would you prefer to consider several more
options?
Ans. No, I want to prefer some more options and choices on my product.

Q4. What price range are you considering?

Ans. 5 lakhs to 20 lakhs

Q5. Are you looking for a family vehicle or vehicle you plan to use for business?
Ans. I am looking for a family vehicle.

Q6. What features are you looking for that your current vehicle doesn’t have?
Ans. Foldable rooftop
1.11 Empathy Map

Map what the users said, thought, felt and did about the problem in this table

What our users were saying? What were our users thinking?

“I want an accurate estimate of how much “I am confused about which car I should
has to be paid for a given vehicle” choose to buy”

“I have no knowledge about cars. What “Is it suitable for long drives ”
should I do to get the best car for me?”
“What if I got scammed!!!! ”

What were our users were doing? How did our users felt?

Going to car showrooms and asking dealers -Confused

about the most commonly used car, or new -Doubtful

cars which are suitable for their budget. -Reluctant

-Troubled
Checking out cars from the internet
-Restlessness
randomly.
-Pensive
 1.12 What were the usual steps that users took related to the problem and
where were the difficulties?

[Link]/buyers usually go to car showrooms and ask the dealers about different cars and their price
range.

[Link] seller decides a price randomly and the buyer has no idea about the car and its value in the present
day scenario.

[Link] buyer gets confused and troubled about which car he should buy, and asks more about features of
cars.

[Link] process is time consuming as the customers have no precise idea about what features they want in
a car.

1.13 Our Team’s problem statement in the format below.

Buyers/Customers and sellers [a specific user or group of users]

were experiencing issues with accurate car price prediction [problem] today

because of incorrect and increased prices of new cars, [cause]

Rate yourself : 4

The Users

1 point - The user group is described but it is unclear how they are affected by the problem.
2 points - Understanding of the user group is evidenced by completion of most of the steps in this section.
3 points - Understanding of the user group is evidenced by completion of most of the steps in this section and
thorough investigation

BRAINSTORMING
1.14 Ideas

How did we use the power of AI/machine learning to solve the users problem by increasing their knowledge or
improving their skills.

AI Idea #1 Personalize learning will help that AI can analyze a user's learning style and adapt
educational content to fit their need

AI Idea #2 AI can create interactive simulations and virtual environments for hands-on learning

AI Idea #3 AI can provide instant feedback on assignments, projects, and exams, helping
users understand their mistakes and learn from them

AI Idea #4 AI can automate repetitive tasks, allowing users to focus on more complex and
creative aspects of their work

AI Idea #5 AI can process and analyze large datasets to uncover patterns and insights that
might be missed by humans
 5.2 Priority Grid
High

High value to users,easy to create High value to users, hard to create

VALUE
TO
USERS

Low value to users,easy to create Low value to users,hard to create

Low
Easy
EASE OF DEVELOPMENT
Hard
1.15 Based on the priority grid, which AI solution was the best fit for our users and
for our team to create and implement?

We have decided upon a CAR PRICE PREDICTION SYSTEM. The advantages of converting

the current system was:

● Gives accurate price of cars.

● Determines the worthiness of cars using a variety of features.

● Saves money

● Saves time

● Improve the efficiency of process

● Improve Customer Satisfaction

● Available 24/7

● Saves money
Rate yourself

Brainstorming

1 point – A brainstorming session was conducted. A solution was selected.

2 points - A brainstorming session was conducted using creative and critical thinking. A solution was selected with
supporting arguments in this section
3 points - A brainstorming session was conducted using creative and critical thinking. A compelling solution was
selected with supporting arguments in this section.

DESIGN
1.16 What were the steps that users will now do using our AI solution to address the
problem?

1. The users with problems on price prediction and budget will start using the model.
2. The model will answer the problems of user’s based on the information.
3. In case the model is not able to answer the question, it will ask to rephrase the question to the user.
4. If the problem is not one of the predefined questions, it will refer the user that we are sorry we can’t find it.

Rate yourself:

Design

1 point – The use of AI is a good fit for the solution.

2 points - The use of AI is a good fit for the solution and there is some documentation about how it meets the needs
of users
3 points - The use of AI is a good fit for the solution. The new user experience is clearly documented showing how
users will be better served than they are today.
 DATA
1.17 What data did we need to train our AI solution?

We need the price of cars, car features, and its fuel type.

1.18 Where or how will you source your data?

Where will Do you have Ethical

the data Who owns the permission to use considerations
Data needed come from? data? the data?

Have
Google forms,
Previous year’s Team Members Yes
data

Want/Need Google Forms,

Previous year’s
data Team Members
Yes

Nice to have
GoogleForms,
Previous year’s Team Members
data
Yes

Rate yourself:

Data

1 point – Relevant data to train the AI model have been identified as well as how the data will be sourced or
collected.
2 points - Relevant data to train the AI model have been identified as well as how the data will be sourced or
collected. There is evidence that the dataset is balanced.
3 points - Relevant data to train the AI model have been identified as well as how the data will be sourced or collected.
There is evidence that the dataset is balanced, and that safety and privacy have been considered.
 PROTOTYPE
1.19 Which AI tool(s) did we use to build our prototype?

PYTHON

1.20 Which AI tool(s) did we use to build our solution?

PYTHON

1.21 What decisions or outputs did our tool generate and what further actions were
needed to be taken after a decision was made?

[Link] with confusion on budget will start using this model.

[Link] model will answer the user’s problem.
[Link] case the model is not able to answer, it will ask the user to
rephrase the problem.
4. Hence it simplifies the car-buying and selling process for all parties involved.

Rate yourself

Prototype

1 points – A concept for a prototype shows how the AI model will work.
2 points - A prototype for the solution has been created and trained.
3 points - A prototype for the solution has been created and successfully trained to meet users’ requirements.
 TESTING
1.22 Who were the users who tested the prototype?

Team members

Students

Customers

1.23 Our observations of our users as they tested our solution.

Customers: Answers should be in simple and precise that it would be sufficient for the users for their
required car

Students: Website links for further exploration to be provided.

Team Members: More simplification on the features of the cars.

1.24 User feedback grid

What works? What needs to change?

Price prediction of cars It works on less data which may give less
accurate output

Questions? Ideas?
Which model is best according to fuel efficiency? We may add more features that it will also give
Which model for long lasting for years? options of warranty, newly launched car
recommendation etc.
 1.25 Refining the prototype: Based on user testing, what needed to be acted on so
that the prototype could be used?

Adding more features recommendation that the user may get his/her favourable car

1.26 What improvements were made later?

The model may prefer car according to the road and locality, may add feature of top of car

Rate Yourself: 4

Testing

1 points– A concept for a prototype shows how it will be tested.

2 points - A prototype has been tested with users and improvements have been identified to meet user
requirements.
3 points - A prototype has been tested with a fair representation of users and all tasks in this section have been
complete
 TEAM COLLABORATION
1.27 How did we actively work with others in our team and with stakeholders?

● Online and Offline sessions with team members for brainstorming.

● Online sessions, surveys, interviews with dealers and owners for gathering data.

● Work divided between various group members.

● Recognizing the contributions of team members and stakeholders.

● Prototype testing done by each member and stakeholders.

● Assigning tasks to other team members based on their strength and expertise.

Rate yourself: 4

Team collaboration

1 point – There is some evidence of team interactions among peers and stakeholders.
2 points - Team collaboration among peers and stakeholders is clearly documented in this section.
3 points - Effective team collaboration and communication among peers and stakeholders is clearly documented in
this section.
INDIVIDUAL LEARNING REFLECTION
11.1. Team Reflections

A good way how we identified what we had learned was to ask ourselves what surprised us
during the project. We Listed the things that surprised us and any other thoughts we might
have on issues in our local community.

Team member name: Shruti Singh

It was a great opportunity to learn and explore the different ways in which we can get
the solution of problem. This model aims to help both the sellers and buyers while
buying a car. Further training the model will help make it better and thus help others in
a better way. It all around helped enhance my knowledge on AI and programing as
well as in other topics. It was a good experience working with the people in the team .

Team member name: Priyanshu & Shreeka

We AI students are expected to give tech based solutions for our organization.
With the help of our project “Car Price Prediction” the problems faced by the
Customers and sellers will be resolved to some extent. Previously , the hand written
informations and sales persons were the main sources to handle all types of queries
but customers were not getting the clear solutions of their queries , other ways need to
be explored. Not only for the current situation, This model will help
The companies lower their burden of delivering the same information again and again.
It will benefit both of them, as it is available 24*7 without any hassles.

Team member name: A. Roshan Baitharu

I have got the best opportunity to show my skills and ideas with others. Everyone enjoy
doing this project and felt very comfortable to have some words to others.
We want the computer to learn from lots of car data to predict prices. Instead of just
human guesses or basic online tools, this system will use machine learning.
This repository showcases a comprehensive machine learning project focused on
predicting the prices of used cars based on various features such as year, fuel type,
transmission type, and more.
 Team member name: P. Vinayak Reddy

This project aims to create an accurate and user-friendly tool that enhances customer
experience and streamlines the pricing process for sales representatives.
It will be used by the management to understand how exactly the prices vary with the
independent variables. They can accordingly manipulate the design of the cars, the
business strategy etc. to meet certain price levels. Further, the model will be a good
way for management to understand the pricing dynamics of a new market.

Rate yourself: 4

Individual Learning Reflection

1 point – Some team members present an account of their learning during the project.
2 points - Each team presents an account of their learning during the project.
3 points - Each team member presents a reflective and insightful account of their learning during the project.
 DATA
CAR DATA GIVEN BY USER TO THE AI MODEL
Car_Name Year Selling_Price Present_Price Kms_Driven Fuel_Type Seller_Type Transmission
ritz 2014 3.35 5.59 27000 Petrol Dealer Manual
sx4 2013 4.75 9.54 43000 Diesel Dealer Manual
ciaz 2017 7.25 9.85 6900 Petrol Dealer Manual
wagon r 2011 2.85 4.15 5200 Petrol Dealer Manual
swift 2014 4.6 6.87 42450 Diesel Dealer Manual
vitara brezz 2018 9.25 9.83 2071 Diesel Dealer Manual
ciaz 2015 6.75 8.12 18796 Petrol Dealer Manual
s cross 2015 6.5 8.61 33429 Diesel Dealer Manual
ciaz 2016 8.75 8.89 20273 Diesel Dealer Manual
ciaz 2015 7.45 8.92 42367 Diesel Dealer Manual
alto 800 2017 2.85 3.6 2135 Petrol Dealer Manual
ciaz 2015 6.85 10.38 51000 Diesel Dealer Manual
ciaz 2015 7.5 9.94 15000 Petrol Dealer Automatic
ertiga 2015 6.1 7.71 26000 Petrol Dealer Manual
dzire 2009 2.25 7.21 77427 Petrol Dealer Manual
ertiga 2016 7.75 10.79 43000 Diesel Dealer Manual
ertiga 2015 7.25 10.79 41678 Diesel Dealer Manual
ertiga 2016 7.75 10.79 43000 Diesel Dealer Manual
wagon r 2015 3.25 5.09 35500 CNG Dealer Manual
sx4 2010 2.65 7.98 41442 Petrol Dealer Manual
alto k10 2016 2.85 3.95 25000 Petrol Dealer Manual
ignis 2017 4.9 5.71 2400 Petrol Dealer Manual
sx4 2011 4.4 8.01 50000 Petrol Dealer Automatic
alto k10 2014 2.5 3.46 45280 Petrol Dealer Manual
wagon r 2013 2.9 4.41 56879 Petrol Dealer Manual
swift 2011 3 4.99 20000 Petrol Dealer Manual
swift 2013 4.15 5.87 55138 Petrol Dealer Manual
swift 2017 6 6.49 16200 Petrol Individual Manual
alto k10 2010 1.95 3.95 44542 Petrol Dealer Manual
ciaz 2015 7.45 10.38 45000 Diesel Dealer Manual
ritz 2012 3.1 5.98 51439 Diesel Dealer Manual
ritz 2011 2.35 4.89 54200 Petrol Dealer Manual
swift 2014 4.95 7.49 39000 Diesel Dealer Manual
ertiga 2014 6 9.95 45000 Diesel Dealer Manual
dzire 2014 5.5 8.06 45000 Diesel Dealer Manual
sx4 2011 2.95 7.74 49998 CNG Dealer Manual
dzire 2015 4.65 7.2 48767 Petrol Dealer Manual
maruti 800 2003 0.35 2.28 127000 Petrol Individual Manual
alto k10 2016 3 3.76 10079 Petrol Dealer Manual
 PROGRAM’S CODE
Objective: Build a system that can recognize emotions from facial
expressions using AI.
Problem Statement: Understanding human emotions is crucial in many
fields, including mental health care, customer service, and human-computer
interaction. However, detecting emotions in real-time through traditional
means, such as verbal communication or self-reporting, is often inefficient
and subjective. This project aims to create an AI-powered emotion
recognition system that uses facial expression analysis to automatically
detect and classify emotions from real-time video inputs. By leveraging
deep learning and computer vision, the system will enhance emotional
awareness in applications like customer support systems, virtual learning
environments, and therapeutic monitoring, providing a more responsive and
empathetic interaction experience.
Key Tools:
Use facial recognition libraries like face_recognition or dlib for detecting facial
features.
Use a pre-trained model or train a CNN (Convolutional Neural Network) on an
emotion dataset like FER2013.
Utilize Python libraries like OpenCV for video capture and real-time emotion
detection.
Features:
Detect emotions like happiness, sadness, anger, etc., in real-time from live
webcam feeds. Display emotion results on the screen.
Store the detected emotions along with a timestamp in a log file for further
analysis.
Python Code:
import cv2
import numpy as np
from [Link] import load_model
from [Link] import img_to_array

# Load pre-trained emotion recognition model (FER2013)

model = load_model('emotion_model.hdf5') # Use a pre-trained model like FER2013

# Emotion classes (can vary depending on the model)

emotion_classes = ['Angry', 'Disgust', 'Fear', 'Happy', 'Sad', 'Surprise', 'Neutral']

# Initialize webcam
cap = [Link](0)

# Load face detector (Haar cascade)

face_cascade = [Link]([Link] + 'haarcascade_frontalface_default.xml')

while True:
ret, frame = [Link]()
if not ret:
break

# Convert frame to grayscale (required for face detection)

gray_frame = [Link](frame, cv2.COLOR_BGR2GRAY)

# Detect faces
faces = face_cascade.detectMultiScale(gray_frame, scaleFactor=1.3, minNeighbors=5)

for (x, y, w, h) in faces:

# Extract face ROI
face_roi = gray_frame[y:y+h, x:x+w]
face_roi = [Link](face_roi, (48, 48)) # Model expects 48x48 input
face_roi = face_roi.astype('float') / 255.0
face_roi = img_to_array(face_roi)
face_roi = np.expand_dims(face_roi, axis=0)

# Predict emotion
prediction = [Link](face_roi)[0]
max_index = [Link](prediction)
emotion = emotion_classes[max_index]

# Draw bounding box and emotion label

[Link](frame, (x, y), (x+w, y+h), (0, 255, 0), 2)
[Link](frame, emotion, (x, y-10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2)

# Show the frame

[Link]('Emotion Recognition', frame)

# Press 'q' to exit

if [Link](1) & 0xFF == ord('q'):
break

[Link]()
[Link]()