[Year]

1
IRA INTERNATIONAL SCHOOL
SESSION 2024-2025

Project on: Face Detection System

Subject: Artificial Intelligence (843)

SUBMITTED TO: SUBMITTED BY:

1. PRINCE NAKARKAR
2.
Mrs. MANGALA MA’AM 3.
JATIN BISHT
SAMYAK KAMKLE
4. PRAGATI SINGH
5. ABISEKH KRISHNA
(Artificial Intelligence Teacher)

CLASS: XII
Roll No –

2
Table of Content

S.no Topic
1 Certificate
2 Acknowledgement
3 Project Name
4 Our motto
5 Introduction
6 Team role
7 Project plan
8 Communication plan
9 Project Definition
10 User Feedback
11 Empathy map
12 Project design
13 Data
14 Prototype
15 Testing
16 Team collaboration
17 Individual reflection
17 Code and Output Screen
18 Video link
18 Bibliography

3
CERTIFICATE

This is to certify that, Pragati Singh student of class XII of

institution IRA INTERNATIONAL SCHOOL, BUTIBORI has
successfully completed his Project on the topic “Face Detection
System” during the academic year 2024-2025 towards partial
fulfilment of credit for the ARTIFICIAL INTELLIGENCE (843)
practical evaluation of 2024-2054 and submitted satisfactory
report, as compiled in the following pages, under my supervision.

Roll No:

___________ _____________

Internal Examiner External Examiner

_______________

Principal

School Seal
Date:- ____________

4
CERTIFICATE

This is to certify that, Jatin Bisht student of class XII of

institution IRA INTERNATIONAL SCHOOL, BUTIBORI has
successfully completed his Project on the topic “Face Detection
System” during the academic year 2024-2025 towards partial
fulfilment of credit for the ARTIFICIAL INTELLIGENCE (843)
practical evaluation of 2024-2054 and submitted satisfactory
report, as compiled in the following pages, under my supervision.

Roll No:

___________ _____________

Internal Examiner External Examiner

_______________

Principal

School Seal
Date:- ____________

5
CERTIFICATE
This is to certify that, Prince Naukarkar student of class XII of
institution IRA INTERNATIONAL SCHOOL, BUTIBORI has
successfully completed his Project on the topic “Face Detection
System” during the academic year 2024-2025 towards partial
fulfilment of credit for the ARTIFICIAL INTELLIGENCE (843)
practical evaluation of 2024-2054 and submitted satisfactory
report, as compiled in the following pages, under my supervision.

Roll No:

___________ _____________

Internal Examiner External Examiner

_______________

Principal

School Seal
Date:- ____________

6
CERTIFICATE
This is to certify that, Abishek krishna student of class XII of
institution IRA INTERNATIONAL SCHOOL, BUTIBORI has
successfully completed his Project on the topic “Face Detection
System” during the academic year 2024-2025 towards partial
fulfilment of credit for the ARTIFICIAL INTELLIGENCE (843)
practical evaluation of 2024-2054 and submitted satisfactory
report, as compiled in the following pages, under my supervision.

Roll No:

___________ _____________

Internal Examiner External Examiner

_______________

Principal

School Seal
Date:- ____________

7
CERTIFICATE
This is to certify that, Samyak Kamble student of class XII of
institution IRA INTERNATIONAL SCHOOL, BUTIBORI has
successfully completed his Project on the topic “Face Detection
System” during the academic year 2024-2025 towards partial
fulfilment of credit for the ARTIFICIAL INTELLIGENCE (843)
practical evaluation of 2024-2054 and submitted satisfactory
report, as compiled in the following pages, under my supervision.

Roll No:

___________ _____________

Internal Examiner External Examiner

_______________

Principal

School Seal
Date:- ____________

8
ACKNOWLEDGEMENT

I wish to express my deep sense of gratitude and indebtedness

to our learned teacher Mrs. Mangala ma’am, TGT
Computer (AI), Ira International School, Butibori for his
invaluable help, suggestions and guidance in the preparation of
this project.
I am also greatly indebted to our principal Mrs. Manisha Sathe
and school authorities for providing me with the facilities and
requisite laboratory conditions for making this Logbook File. I
also extend my thanks to the teachers, my
classmates and friends who helped me to complete project

successfully.
Team Member
● Prince Naukarkar
● Jatin Bist
● Pragati Singh
● Abishek Krishna
● Samyak Kamble

9
AI PROJECT LOGBOOK
PROJECT NAME: Face Detection System

SCHOOL NAME: Ira International School

CLASS/YEAR: XII / 2024-2025

TEACHER NAME: Mangala ma’am

TEACHER EMAIL: [email protected]

TEAM MEMBER NAMES AND GRADES:

1. Pragati Singh

2. Jatin Bisht

3. Samyak Kamble

4. Abishek Krishna

5. Prince Naukarkar
OUR MOTTO

We felt that Indian schools require improved accuracy and

accessibility in student identification which identifies

students and complete services without student’s needs to

swipe card, enter a key code or sign a sheet and secondly for

attendance management. It can even be used for contactless

payments, security and cheating detection during exams. It

would add beauty to already fantastic schools. So this factor

became our motivation to design a project on face detection

which can become an initiative step.

9
introduction
Our capstone project revolves around face detection,

using Jupyter Notebook and OpenCV to develop a

working system. While we didn’t use a direct face

detection library, we implemented page detection tools

integrated with the camera, like a webcam, for real-time

image capturing and processing. Through various tests

and calibrations, we fine-tuned the system to accurately

detect and recognize faces under different conditions,

such as lighting and angles. This project demonstrates the

practical use of AI in everyday scenarios and highlights

the growing capabilities of machine learning in creating

smarter, more efficient technologies

10
Applications of Face Detection AI
1. SURVEILLANCE AND SECURITY:
Real-time face tracking and detection in CCTV footage: In public and
private spaces, face detection AI is extensively used for monitoring and
security purposes. This involves analyzing video streams from CCTV
cameras to detect and track faces in real time. Security systems can flag
suspicious individuals or detect repeat offenders using databases of
known criminals or persons of interest.

2. PUBLIC SAFETY:
Face detection AI can alert law enforcement. agencies about the
presence of wanted individuals in pubic spaces, airports, or
border checkpoints.
3. Access control:

In secure facilities (offices, banks, labs), face detection is used

for controlling entry points. Only recognized personnel can gain
access, adding an extra layer of security beyond key cards or
passcodes.

4. Crowd analysis:

In large gatherings like sports events or concerts, face detection

helps authorities manage crowds and detect potential threats early by
recognizing anomalies in real time.

11
5. SMARTPHONES:
Face unlock features: Most modern smartphones feature face
recognition systems that use face detection AI to authenticate
users. This biometric method allows users to unlock their
phones by simply looking at the device. The AI compares the
user’s face to the data stored during the initial setup.
3D face scanning: High-end smartphones like iPhones and
some Android devices use 3D scanning techniques to detect
depth and facial features, making face unlocking more
secure and less prone to spoofing.

User experience: Face detection also enhances other

smartphone experiences, such as adjusting screen brightness
based on whether the user is looking at the screen.

12
6. SOCIAL MEDIA AND PHOTO APPS:
Auto-tagging and face recognition in photos: Social media
platforms like Facebook and Instagram utilize face detection to
automatically identify individuals in photos, making it easier for
users to tag their friends. These systems analyze facial features from
photos, compare them to a database of known faces, and suggest
tags.
Facial filters and effects: Platforms like Snapchat and Instagram use
face detection for augmented reality (AR) filters, applying
fun effects, masks, or animations to users' faces in real-time. Photo
organization: Google Photos and Apple Photos use face detection to
organize images, automatically grouping photos of the same person,
which simplifies searches and browsing by specific individuals.
7.RETAIL AND MARKETING:

Identifying customer demographics for targeted advertising: Face detection AI

is becoming increasingly common in retail environments where businesses aim
to enhance customer experience and target advertisements. By detecting and
analyzing faces, AI can identify a customer’s age group, gender, and emotional
state (e.g., happy, neutral, frustrated) while they

13
1. HEALTHCARE:

Patient monitoring and analysis: In hospitals and care

facilities,
face detection AI can be used to monitor patients’ expressions
and emotional states. It can track whether a patient is in pain,
showing signs of anxiety, or distress,

14
: 1. OpenCV for Face Detection
OpenCV (Open Source Computer Vision Library) is widely
used for face detection tasks due to its simplicity, speed, and
lightweight nature. It is based on traditional machine learning
techniques like Haar Cascades or LBP (Local Binary Patterns),
which have been in use for over a decade.
Speed: OpenCV is fast and efficient, making it an excellent
choice for real-time face detection applications, such as:
Webcam-based face detection.
Live security monitoring systems.
Embedded systems where computational power is limited, such
as Raspberry Pi-based surveillance systems.
Basic Applications: OpenCV is ideal for basic face

detection tasks that do not require complex facial analysis like

detecting emotions or facial landmarks (eyes, nose, etc.). In simple
use cases, it can detect faces from a webcam feed or an image with
good accuracy and reasonable performance.

15
Common Uses of Webcams in Face Detection
1.Real-Time Surveillance:

Webcams are often employed in security systems for real-time

face tracking and recognition. They can detect multiple faces

within a frame and compare them against a database of known

faces for identification. This can be used in access control systems

or in environments that require heightened security, such as

offices or banks.

2. Biometric Authentication:

Many laptops and mobile devices use webcams with integrated

infrared sensors to perform biometric face recognition for login

systems. This adds an extra layer of security compared to

passwords, as it’s more difficult to replicate a person’s face

than to guess a password.

3. Human-Computer Interaction (HCI):

Webcams are used in HCI systems to detect faces and even track

eye movements. This allows for gesture-based control of

computers or devices, where users can interact

16
TEAM ROLES

Role Role description Team Member Name

● Schedules and allocates
tasks among the team

● Ensures tasks are

Leader
completed on time

● Acts as the point of contact

between the team and the Prince
teacher, users and
stakeholders

● Resolve team issues

● Decides on type of data

Data expert
needed to train an AI
model

● Collects data

● Ensures data is in a
format that the team can Jatin
work with

● Ensures data is ethically

sourced and unfair bias is
eliminated Works with
prototype builder to train the
AI model

17
● Collects questions from
the team that
need answers
Information
● Identifies where
researcher
answers can be
located (source) Pragati
Searches for
answers, writes
up a report and
passes information
to the project
reporter

● Films the activities of the

Video producer team and edits these Abishek

into a presentation for
submission

18
● Works with the team and
Designer
the user to create a
process flow for the new
user experience Abishek

● Plans the user

interface for the
prototype

● Works with data

Prototype
expert to train/teach
builder
computer
/Cod er Prince
● Creates the prototype and
codes if necessary

Works with users to

tests the prototype
Tester
Gets feedback from
users and user sign-off
when they prototype has Samyak
met user requirements

Creates an action plan

on what needs to be
fixed and prioritizes
requests for future
improvements

19
PROJECT
PLAN

20
Team

Team

Team

Team

Team
Team

21
22
Team

23
Communications plan

Communication mode:
Mixture of both offline and online

Frequency of meetings:
Once in a month

Person responsible for setting up online document and othercontribution:

Team leader

TEAM MEETINGS
Date of meeting: April 13
Who attended: All team member
Purpose of meeting: Discuss initial ideas and project plan

Items discussed:
1.reviewed ideas for the face detection project
2. discussed goal and objective for each phase 3.
planned initial task for project preparation

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

1. complete
coursework andreading
2. set up shared drive folder

24
Date of Meeting: May 5
Who attended: All team members
Who wasn’t able to attend: None
Purpose of Meeting: Finalize problem statement and discuss communityresearch

Items Discussed:
1. Presented findings from community research on potential applications
2. Defined the specific problem statement for the project
3. Outlined next steps for understanding user needs

Date of Meeting: June 7

Who attended: All team members
Who wasn’t able to attend: None
Purpose of Meeting: Review brainstorming outcomes and select the best approach

Items Discussed:
1. Reviewed ideas generated for different face detection methods
2. Narrowed down ideas to the most feasible solution
3. Set timeline for solution design phase

Date of Meeting: June 25

Who attended: All team members

Who wasn’t able to attend: None
Purpose of Meeting: Review design and architecture of the solution

Items Discussed:

1. Analyzed the proposed architecture for face detection

2. Made adjustments to the design based on team feedback
3. Finalized the requirements for data collection

25
Date of Meeting: September 12
Who attended: All team members
Who wasn’t able to attend: None
Purpose of Meeting: Analyze user feedback and make improvements

Items Discussed:
1. Discussed feedback received from user testing sessions
2. Identified areas for model improvement based on feedback
3. Outlined final adjustments before project presentation

Date of Meeting: October 8

Who attended: All team members
Who wasn’t able to attend: None
Purpose of Meeting: Review presentation and documentation for submission

Items Discussed:

● Reviewed the final presentation slides and flow

● Verified completeness of project documentation
● Assigned tasks for final preparations

26
PROBLEM DEFINITION

3.1 List important local issues faced by your school or community

1. Limited Technical Knowledge: Many students and teachers had

a lack of familiarity with face detection technology, making it difficult to
effectively engage with and implement the project.

2. Inadequate Hardware Resources: The available computer systems

in the school were not powerful enough to run the face detection algorithms
efficiently, leading to slow processing times and limiting the project's feasibility.

3. Dataset Availability: We struggled to find suitable datasets for training

the face detection model, as most available datasets did not accurately represent
the diversity of faces in our school community, impacting the model's
performance.

3.2 Which issues matter to you and why?

Limited technical knowledge mattered to us because it directly impacted our ability to

effectively collaborate on the project. If students and teachers were not familiar with face
detection technology, they would find it challenging to contribute ideas, understand the
project’s objectives, and utilize the system effectively. This gap in knowledge could hinder the
project's overall success and limit the potential benefits of the technology within the school.
By addressing this issue through educational initiatives, we aimed to empower our peers,
foster a collaborative environment, and ensure everyone felt included in the project’s
development.

3.3 Which issue will you focus on?

Educational Workshops
Resource Development
Peer Support

27
Rate yourself
5
Problem Definition

1. point - A local problem is described

2. points - A local problem which has not been fully solved before is
described.

28
THE USERS

4.1 Who are the users and how are they affected by the problem?

● Students: Limited technical knowledge hindered their engagement and ability

to utilize the system effectively.

● Teachers: Difficulty integrating the technology into lessons due to

unfamiliarity affected their teaching method.

● School Community: Concerns about the technology's implementation

led to reluctance in participation, impacting the project's overall acceptance

4.2 What have you actually observed about the users and how the problem affects them?

● Eagerness to Learn: Students were motivated to understand face detection with proper
training.

● Need for Support: Teachers required ongoing assistance to integrate the technology.

● Concerns About Privacy: The community was cautious about privacy issues,
needing clear communication.

29
Empathy Map

What our users are saying What our users thinking

"I want to learn how face detection "Will my privacy be protected?"

works."

"Can I trust this technology?"

"How can this help in our school?"

"What if it doesn't recognize my

"Is it easy to implement in class?" face?"

What our users are doing How our users feel

Participate in workshops Curious about the technology.

and training sessions.

Eager but nervous about using it.

Experiment with the
face detection system.
Frustrated when the system has
issues
Seek help from teachers
and peers.

30
Rate yourself
4.5
The Users

● point - The user group is described but it is unclear how they are affected by the problem.

● points - Understanding of the user group is evidenced by completion of most of the

steps in thissection.

31
Design
Prototype Designing Steps for Face Detection Project

● We defined requirements: We identified the key features and functionalities

needed for the face detection prototype

● We designed the architecture: We outlined the system architecture, including

input sources and processing components.

● We developed the prototype: We created a basic version of the face

detection system using Jupyter Notebooks and OpenCV.

● We implemented image processing: We applied image preprocessing

techniques such as resizing and converting to grayscale.

● We integrated the detection algorithm: We used simple OpenCV functions

to develop the face detection logic.

● We set up real-time capture: We incorporated webcam functionality

for real-time video processing and face detection.

● We enabled user interaction: We allowed users to upload images for testing

the face detection feature

● We conducted testing: We tested the prototype with various images and

video feeds to evaluate detection accuracy.

Rate yourself 4.5

Design 3.5

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

● points - The use of AI is a good fit for the solution and there is some documentation about how
itmeetsthe needs of users

32
DATA
7.1 What data will you need to train your AI solution?

You will need real-time video feed from the webcam to detect faces. No pre-collected
image dataset is required as the data will be captured live during the face detection
process.

33
Rate yourself 4

Data

● point – Relevant data to train the AI model have been identified as well as how the
data will besourcedor collected.

● points - Relevant data to train the AI model have been identified as well as how the
data will besourcedor collected. There is evidence that the dataset is balanced.

● points - Relevant data to train the AI model have been identified as well as how the data will be sourced or

34
PROTOTYPE

8.1 Which AI tool(s) will you use to build your prototype?

You used OpenCV for face detection, Jupyter Notebooks as the development
environment, and a Webcam for live video feed.

8.2 Which tool(s) will you use to build your solution?

The same tools: OpenCV, Jupyter Notebooks, and Webcam.

8.3 What decisions or outputs will your tool generate and what further action needs to be taken
after a decision is made?

The tool will output real-time detection of faces within the video feed. Once a face is
detected, it will be highlighted with a bounding box. No additional action is required
beyond the detection unless further functionalities, like face recognition or other
triggers, are added later.

35
TESTING

9.1 Who are the users who tested the prototype?

The prototype was tested by Abisekh who used their webcam to check if the
face detection worked in real-time. You may also include any other people
who helped in testing the accuracy of the detection.

9.2 List your observations of your users as they tested your solution.

Users found that the face detection worked in most cases when facing the
webcam directly.

The face detection was responsive and detected faces in various lighting
conditions.

Detection was less accurate when the user’s face was turned sideways or
obscured by objects.

Users appreciated the simplicity and ease of use of the prototype. Some
suggested adding functionality for recognizing faces, not just detecting them.

36
TEAM COLLABORATION

Working together as a team on the Face Detection Model project was an enriching
and memorable experience. From the very beginning, we ensured that each
member had a defined role based on their strengths and interests, which allowed us
to work efficiently while valuing everyone’s contributions. Regular meetings
helped us discuss progress, brainstorm ideas, and solve challenges collaboratively.
Tasks were divided effectively—some focused on research and data collection,
others on coding and debugging, and a few on preparing the presentation and
report.
This division of work ensured that everyone played a crucial role
in the project’s success.
The experience taught us the importance of teamwork and collaboration. While
we faced challenges, such as understanding complex algorithms and debugging
errors, these obstacles became opportunities for growth. Solving problems
together not only enhanced our technical knowledge but also strengthened our
bond as a team. Completing the project successfully and seeing our model detect
faces accurately was a moment of pride for all of us.
We also gained valuable soft skills like time management, communication, and
decision-making. Overall, this project showed us the power of collective effort and
inspired us to appreciate the value of working together toward a common goal.

Rate yourself

Team collaboration

4 point – There is some evidence of team interactions among peers and stakeholders.

5 points - Team collaboration among peers and stakeholders is clearly documented in this section.3 points -

37
INDIVIDUAL LEARNING REFLECTION

11.1. Team Reflections

Team member name: PRINCE
Working on the face detection project was a challenging yet rewarding experience. I was
fascinated by the technical intricacies involved, particularly in using OpenCV to implement the
detection algorithms. Initially, I struggled with understanding how the model processed image
data, but through research and trial-and-error, I developed a strong grasp of the concepts.
One memorable moment was debugging an issue with accuracy that taught me the
importance of testing under various conditions.
This project reinforced my belief that persistence and collaboration are key to overcoming
obstacles in technical endeavors.

Team member name: PRAGATI

This project was a unique opportunity to collaborate with my teammates, and it taught me the
importance of effective communication. Each of us brought different strengths to the table,
and I enjoyed brainstorming solutions together when we encountered challenges. One aspect
I particularly valued was how we divided tasks, which allowed me to focus on training the
model while others worked on data collection and interface design. The experience made me
realize how crucial teamwork is in delivering a successful project, and I feel more confident
about working in team-based environments in the future.

Team member name: JATIN

As we worked on the face detection project, I became increasingly aware of the ethical
implications of this technology. While it has immense potential to improve security and
accessibility, it also raises concerns about privacy and misuse. One thing that stood out to me
was the bias in datasets—we
discovered that without diverse training data, the model’s accuracy could be significantly
affected for certain groups. This realization made me more critical of the technologies we
create and their societal impact. It was a thought-provoking journey that left me committed to
promoting ethical practices in AI.

38
Team member name :ABISHEK

The face detection project pushed me out of my comfort zone, particularly when it came to
learning new programming tools. I had little experience with machine learning before this, so
the steep learning curve was initially intimidating. However, with guidance from my
teammates and online
resources, I gradually built confidence. I feel proud of how much I’ve grown technically and
personally through this process. This project also taught me the importance of adaptability, as
we had to refine our approach multiple times to address unexpected challenges.

Team member name :SAMYAK

Working on this project made me think deeply about how technology like face detection can
impact our local community. I was struck by how it could improve security systems, but I also
became mindful of the potential risks, such as surveillance overreach. Balancing innovation
with responsibility was a recurring theme throughout our work, and it has shaped how I view
technology development. This experience inspired me to explore ways to make technology
more accessible and equitable for
everyone. I feel proud of what we’ve achieved and look forward to applying these lessons in
future
projects.

Rate yourself

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.

39
import cv2
# Load the pre-trained Haar Cascade classifier for face detection
face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

# Open the webcam (0 is usually the default webcam)

cap = cv2.VideoCapture(0)

# Check if the webcam is opened correctly

if not cap.isOpened():
print("Error: Could not access the camera.")
exit()

while True:
# Capture frame-by-frame
ret, frame = cap.read()

# If frame is not read correctly, break the loop

if not ret:
print("Error: Failed to capture image.")
break

# Convert the image to grayscale (Haar Cascade requires grayscale images)

gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

# Detect faces in the image

faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5, minSize=(30, 30))

# Draw rectangles around the faces

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

cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 2)

# Display the resulting frame with face detection

cv2.imshow('Face Detection - Live', frame)

# Exit the loop when 'q' is pressed

if cv2.waitKey(1) & 0xFF == ord('q'):
break

# Release the capture object and close all windows

cap.release()

40
41
VIDEO LINK

Enter the URL of your team video: https://youtu.be/K-a120sJ4HE?feature=shared

42
VIDEO PRESENTATION

Points Given

Criteria 3 –
excellen
t 2 –
very
good

1 – satisfactory

Communicati The video is well-paced and communicated, following a clear and

on logical sequence.

Illustrative Demonstrations and/or visuals are used to illustrate

examples, where appropriate.

Accur The video presents accurate science and technology and uses
ate appropriate language.
langu
age

Passion The video demonstrates passion from team members about their
chosen topic/idea.

Sound and
The video demonstrates good sound and image quality.
image quality

Length The content is presented in the video within a 3-minute timeframe.

Total points

43
44