VISVESVARAYA TECHNOLOGICAL UNIVERSITY

Jnana Sangama, Belagavi - 590018

A DIP MINI PROJECT REPORT ON

“VOLUME CONTROL WITH HAND DETECTION”

Submitted in the partial fulfillment of the requirement for the sixth semester of

BACHELOR OF ENGINEERING
In
ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
BY
CHETHAN K (1RR20AI007)
K CHANDAN(1RR20AI011)

Under the guidance of

MAMATHA K R
Associate Professor,
Dept. of AIML,
RRCE

DEPARTMENT OF ARTIFICIAL INTELLIGENCE AND MACHINE

LEARNING

RAJARAJESWARI COLLEGE OF ENGINEERING

MYSORE ROAD, BANGALORE-560074
(An ISO 9001:2008 Certified Institute)
(2022-23)
 RAJARAJESWARI COLLEGE OF ENGINEERING
MYSORE ROAD, BANGALORE-560074
(An ISO 9001:2008 Certified Institute)
(Affiliated to Visvesvaraya Technological University, Belagavi)
DEPARTMENT OF ARTIFICIAL INTELLIGENCE AND MACHINE
LEARNING

CERTIFICATE
“VOLUME CONTROL WITH HAND DETECTION”
Carried out by

CHETHAN K (1RR20AI007)
K CHANDAN(1RR20AI011)

The students of “Rajarajeswari College of Engineering” in partial fulfillment for the sixth
semester of Bachelor of Engineering in Artificial Intelligence and Machine Learning of the
Visvesvaraya Technological University, Belagavi during the year 2023. It is certified that all
corrections/suggestions indicated for Internal Assessment have been incorporated in the report
deposited in the departmental library. The mini project report has been approved as it satisfies
the academic requirements in respect of mini project work prescribed for the sixth semester.

……………………… ……………………………

Signature of guide Signature of HOD

[MAMATHA K R] [Dr. K S RAJESH]
Assistant Professor, Dept. of AIML Prof. & HOD, Dept. of AIML
RRCE, Bangalore RRCE, Bangalore

External Viva-Voce
Name of the examiners: Signature with date:

1. 1.
2. 2.
 ACKNOWLEDGEMENT

I am truly thankful and convey my sincere gratitude to the principal, Dr. R

Balakrishna Rajarajeswari College of Engineering, Bangalore.

I convey my sincere gratitude to Dr. K S Rajesh, HOD, Department of

Artificial Intelligence and Machine Learning for his meticulous support,
continuous co- operation, valuable suggestion and encouragement during the
development of the project. I also extend my thanks for his invaluable guidance
to imbibe the requisite knowledge for success of our project.

I convey my sincere gratitude to Mamatha K R, Assistant Professor, Department

of Artificial Intelligence and Machine Learning, for her meticulous support
continuous co-operation, valuable suggestion and encouragement during the
development of the project. I also extend my gratitude for her guidance to imbibe
the requisite knowledge for success of my project, as an internal guide. I am very
much obliged.

I also thank my parents who have encouraged me and supported me in every stage
of development of this project.

Last but not the least, my wishes to the entire Artificial Intelligence and Machine
Learning for their help and guidance, encouragement, inspiration and co-
operation at all stages of the development of this project without which this
project wouldn’t have been a success.

Finally, I express my heartfelt gratitude to all those who helped me to complete

the project work successfully by providing support, suggestions, advise, guidance
and much needed encouragement.

CHETHAN K(1RR20AI007)
K CHANDAN(1RR20AI011)
RAJARAJESWARI COLLEGE OF ENGINEERING
MYSORE ROAD, BANGALORE-560074

DECLARATION
I, Chethan k and K Chandan the student of sixth semester B.E, Department of Artificial
Intelligence and Machine learning, Rajarajeswari college of Engineering, Mysore Road,
Bengaluru, declare, that the Project Work entitled “VOLUME CONTROL WITH
HAND DETECTION” has been carried out by and submitted in partial fulfillment of the
requirement of 6th semester 2023. The matter embodied in this report has been submitted
to any university or institute for the award of any other degree or diploma.

Place: Bengaluru CHETHAN K [1RR20AI007]

K CHANDAN[1RR20AI011]

Date:
 ABSTRACT

The “Volume Control With Hand Detection Using Digital Image Processing
with Python" project aims to develop volume controlling of the device with the
help of the camera using the tips for our thumb and index finger. This project
leverages the power of digital image processing techniques implemented using
the Python programming language.

We can use our hand gestures to control the basic operation of a computer like
increasing and decreasing volume. Therefore, people will not have to learn
machine-skills which are a burden most of the time.

The purpose of this project is to discuss a volume control using hand gesture
recognition system based on detections of hand gestures .

The main aim is to create a system which can identify the human hand gestures
and use same input as the information for controlling the device and by using
real time gesture.

In this project we are developing a hand detection volume controller system

with the help of python.
 TABLE OF CONTENTS

1. INTRODUCTION 1

2. RELATED WORK 2

3. LITERATURE STUDY 2

4. SOFTWARE REQUIREMENT 3

5. SYSTEM ARCHITECTURE 4

6. LIBRARY AND PACKAGES 6

7. ADVANTAGES AND DISADVANTAGES 7

8. GUIDING PRINCIPLES 8

9. SNAPSHOT 9

10. FUTURE SCOPE 10

11. CONCLUSION 11

12. REFERENCES 12
 INTRODUCTION

Hand gestures is the powerful communication medium for Human computer

interaction .Several input devices are available for interaction with computer, such
as keyboard, mouse, joystick and touch screen, but these devices does not provide
easier way to communicate .
Gesture recognition helps computers to understand human body language. This
helps to build a more potent link between humans and machines,rather than just
the basic text user interfaces or graphical user interfaces (GUIs).In this project for
gesture recognition, the human body’s motions are read by computer camera.
The computer then makes use of this data as input to handle applications. The
objective of this project is to develop an interface which will capture human hand
gesture dynamically and will control the volume level.
The challenging part in this systems is background images or videos which is
recorded or captured during taking the inputs i.e. hand gesture by the user, also
some time lightning effect the quality of this input taken which creates the problem
in recognizing.

Dept Of AIML,RRCE 1
 RELATED WORK

In vision community hand gesture is an active area of research, for the purpose of
sign language recognition and human computer interaction. In this we have used
some algorithms and some modules to detect the gestures of the person and these
gestures are taken as the input in the system . Here, several modules are used like
opencv-python, mediapipe, numpy etc for the purpose of tracking the gestures.

After capturing the input from the user the image is used in the hand tracking
system to check the dimensions and shape of the gesture which is received in the
system.

Hand tracking module plays a important role in identifying the input recorded in
the system, after that classification and segmentation process is used to classify the
gestures in the system .Machine learning and deep learning is also used to identify
the training data from the system and identify it according to the requirement of
the system .After this the gestures are identified from the trained data and on the
basis of that data the gestures rae recognized and is used for processing of the the
system to implement the functions like increase and decrease in volume.

LITERATURE STUDY

As per various literature surveys it is found that for implementing this project the
basic concepts involved are:
1. Hand Detection and Localization
2. Image Preprocessing Techniques
3. Image Thresholding
4. Convex Hull Analysis
5. Finger Segmentation
6. Finger Tracking Algorithms
7. Real-time Video Processing
8. Python Libraries for Image Processing (OpenCV, NumPy, scikit-image)

Dept Of AIML,RRCE 2
 SOFTWARE REQUIREMENTS

ANACONDA
It is a free and open source distribution of the Python for data science and machine
learning related applications (large-scale data processing, predictive analytics,
scientific computing), that aims to simplify package management and
deployment. Package versions are managed by the package management system.
The Anaconda distribution is used by over 6 million users, and it includes more
than 250 popular data science packages suitable for Windows, Linux, and
MacOS.

JUPYTER NOTEBOOK
The Jupyter Notebook is an open source web application that you can use to create
and share documents that contain live code, equations, visualizations and text.
Jupyter notebook is maintained by the people at project Jupyter. Jupyter
notebooks are a spin of project from the IPython project, which used to have an
IPython notebook project itself.

HARDWARE INTERFACES:
1. Processor: Intel CORE i7 processor with minimum 2.9 GHz speed.
2. RAM: Minimum 4 GB.
3. Hard Disk: Minimum 500 GB

SOFTWARE INTERFACES:
1. Python Programming Language
2. OpenCV framework
3. Windows 11
4. MediaPipe library
5. Time library

Dept Of AIML,RRCE 3
 SYSTEM ARCHITECTURE

In this project we are using python technology to develop the project , the code
is written and designed in python language using Opencv and NumPy modules.
In this project firstly we import the libraries which are to be used for further
processing of the input and the output. The libraries which are used in this
project which needs to be imported are OpenCV, mediapipe, math, ctypes,
pycaw and numpy.We get video inputs from our primary camera.

Now, here mediapipe is used to detect the video as the input from our camera
and use mphand.hands module to detect the gesture .Then , in order to access the
speaker we have used the pycaw and we have provided the range of the volume
from minimum volume to maximum volume.

Next step is to convert the input image to rgb image to complete the processing
of the input captured. Then its turn to specify the points of thumb in input and
fingers.

Volume range id processed using the hand range in this process numpy is used
to convert this process and process the required output. NumPy package is
fundamental package for computing in Python language. It is consist of
several things like-
• powerful N-dimensional array
• object broadcasting
• tools to integrate C.
• Fourier transform, and random number capabilities

Dept Of AIML,RRCE 4
 ➢ System Architecture

Dept Of AIML,RRCE 5
 THE LIBRARY AND PACKAGE

1. MEDIAPIPE

MediaPipe is a framework that provides customizable Machine Learning (ML)

solutions (such as face and hand detection, hair segmentation, motion tracking, etc.)
for live and streaming media. Their solution for hand detection and tracking is
called MediaPipe Hands, and it employs ML to provide palm detection and a hand
landmark model which consists of 21 3D landmarks, as shown in Figure.

These 3D landmarks are each composed of x, y, and z coordinates. x and y

correspond to the landmark position, normalized from 0 to 1 by the image’s width
and height, respectively. The z component represents how close the landmark is to
the camera. We will only use the x and y coordinates in this tutorial. Additionally,
the solution provides a label related to the predicted handedness of the detected
hand, indicating left or right.

2. OPENCV

OpenCV (Open Source Computer Vision Library) is a library of programming

functions mainly for real-time computer vision. Originally developed by Intel, it
was later supported by Willow Garage, then Itseez (which was later acquired by
Intel). The library is cross-platform and licensed as free and open-source

Dept Of AIML,RRCE 6
 software under Apache License 2. Starting in 2011, OpenCV features GPU
acceleration for real-time operations.

3. NUMPY

Is the module of the Python. The numpy word basically shows Numerical Python
and it is utilized. This is the module which is basically written in c language and is
said as expansion module . Numpy guarantee remarkable execution speed. Numpy
is mostly used for performing calculations, tasks using certain functions it provides
like multiply, divide, power etc.

4. IMAGE FILTERING -HISTOGRAM

Histogram is a type of graph which represents the movement of the pixels power
in the portrayal. In this we use to filter the images using histogram and convert
them into the rgb in order to process the image in our system . Consequently the
power of a pixel is in the range [0,255].

ADVANTAGES:

• Easy to use
• Hassle free
• Fun to use
• More interactive

DISADVANTAGES:

• Can’t be used for long distance

• Sometimes not accurate
• Requires a decent camera
• May be confused by two palms

Dept Of AIML,RRCE 7
 GUIDING PRINCIPLES

1. Non-intrusive and Contactless: The finger counter detection system

based on digital image processing does not require any physical contact
with the fingers being counted. This non-intrusive nature makes it more
hygienic and suitable for various applications where physical contact
may not be desirable, such as healthcare, public spaces, or interactive
displays.

2. Scalability and Adaptability: The use of Python for implementing the

finger counter detection system allows for easy scalability and
adaptability. Python offers a wide range of libraries and frameworks for
image processing, computer vision, and machine learning, which can be
leveraged to enhance the system's capabilities or adapt it to different
environments and requirements.

3. Accuracy and Reliability: Digital image processing techniques, when

properly implemented and calibrated, can provide accurate and reliable
finger counting results. By leveraging advanced image processing
algorithms and techniques, the system can handle variations in lighting
conditions, hand orientations, and different finger shapes, improving
overall accuracy.

4. Accessibility: The use of Python as the programming language for the

project makes it accessible to a wide range of developers and researchers.
Python has a simple and intuitive syntax, a vast community of developers,
and extensive documentation, making it easier for individuals to
contribute, modify, and expand the finger counter detection system.

5. Versatility and Applications: The developed finger counter detection

system can have numerous applications across various domains. It can be
used in interactive displays, sign language recognition, hand gesture-based
interfaces, fitness tracking, virtual reality, augmented reality, and more.
The versatility of the system opens up possibilities for innovative and
interactive user experiences.

Dept Of AIML,RRCE 8
 SNAPSHOT

Dept Of AIML,RRCE 9
 FUTURE SCOPE

While the current implementation of the finger counter detection system offers
valuable advantages and capabilities, there are several avenues for future
development and expansion such as:

1. Enhanced Accuracy and Robustness: Further research can focus on

improving the accuracy and robustness of the finger counter detection system.
This can involve exploring advanced image processing techniques, machine
learning algorithms, or deep learning approaches.

2. Real-time Gesture Recognition: Expanding the project to include real-time

gesture recognition capabilities can open up opportunities for various
interactive applications. By combining the finger counter detection system
with machine learning algorithms, it becomes possible to recognize specific
gestures or hand poses, enabling more advanced interactions in virtual reality,
augmented reality, or gaming scenarios.

3. Mobile and Embedded Systems Integration: Adapting the finger counter

detection system for mobile devices or embedded systems can enhance its
portability and usability. This can involve optimizing the algorithms for
resource-constrained environments, leveraging dedicated hardware
accelerators.

4. Integration with Existing Systems: Exploring the integration of the finger

counter detection system with other existing systems or applications can
unlock new possibilities. For example, integrating it with healthcare
monitoring systems, sign language recognition platforms, or human-
computer interaction frameworks can enable seamless and innovative
applications.

5. Usability and Accessibility Improvements: Consideration should be given

to making the system more accessible to a wider range of users.

Dept Of AIML,RRCE 10
 CONCLUSION

This project is presenting a program that allows the user to perform

hand gesture for convenient and easier way to control the software .A
gesture based volume controller doesn’t require some specific type of
markers and these can be operated in our real life on simple Personal
Computers with a very low cost cameras as this not requires very high
definition cameras to detect or record the hand gestures. Specifically,
system tracks the tip positions of the counters and index finger of each
hand.The main motive of this type of system is basically to automate
the things in our system in order to make the things become easier to
control. So in order to make it realiable we have used this system to
make the system easier to control with the help of these applications.

Dept Of AIML,RRCE 11
 REFERENCES

1. S. Sridhar, Digital Image Processing, Oxford University

Press, 2ndEdition, 2016.

2. Tom M. Mitchell, Machine Learning, McGraw-Hill Education, 2013

3. Aurelien Geron, Hands-on Machine Learning with Scikit-

Learn &Tensor Flow, O’Reilly, Shroff

4. Publishers and Distributors Pvt. Ltd 2019

Dept Of AIML,RRCE 12