International Journal of Research in Engineering and Science (IJRES)
ISSN (Online): 2320-9364, ISSN (Print): 2320-9356
www.ijres.org Volume 11 Issue 5 ǁ May 2023 ǁ PP. 154-160
Gesture Volume Control
1
Prof.P Ajitha
2
Irfan Ahmed M N
3
Mohith Seshan K M
4
Siva C
1.
Assistant Professor, Department Of Computer Science and Engineering, St. Xavier’s Catholic College
Of Engineering.
2.
Student, Department Of Computer Science and Engineering, St. Xavier’s Catholic College Of
Engineering.
3.
Student, Department Of Computer Science and Engineering, St. Xavier’s Catholic College Of
Engineering.
4.
Student, Department Of Computer Science and Engineering, St. Xavier’s Catholic College Of
Engineering.
ABSTRACT
The aim of this project is to develop a gesture-based volume control system using Python programming
language and several libraries, including OpenCV, Mediapipe, PyCaw and NumPy. The system is designed to
allow users to adjust the volume of their computer by making hand gestures in front of a camera. The project uses
Mediapipe, a machine learning framework, to detect and track the user's hand movements and recognize
specific gestures thatcorrespond to volume adjustments. OpenCV is used for camera input and image
processing, allowing the systemto capture and analyze the user's hand movements in real-time. NumPy is used
for data manipulation and processing, while PyCaw provides a Python interface to the Windows CoreAudio API,
allowing the system to interact with the computer's audio system. The system consists of three main components:
hand detection and tracking, gesture recognition, and volume control. Hand detection and tracking are
implemented using Mediapipe's hand tracking module, which detects the user's hand and provides a set of
landmarks representing the hand's position and orientation Gesture recognition is implemented using a simple
machine learning algorithm that classifies the user's hand gestures based on the positions of the hand
landmarks. Finally, volume control is implemented using PyCaw to adjust the system's audio volume based on
thedetected hand gestures. The project provides an intuitive and efficient wayfor users to adjust their computer's
audio volume without the need for a physical input device. It also demonstrates the potential of machine learning
and computer vision technologies for developing novel andinteractive user interfaces.
Keywords:
Gesture-based volume control system, Python programming language, OpenCV,Mediapipe, PyCaw, NumPy,
hand detection.
----------------------------------------------------------------------------------------------------------------------------- ----------
Date of Submission: 25-04-2023 Date of acceptance: 05-05-2023
----------------------------------------------------------------------------------------------------------------------- ----------------
I. INTRODUCTION
Gesture volume control is a cutting-edge technology that allows users to adjust the volume of their
devices without the need for physical buttons. With this technology, userscan simply make hand gestures in the
air to increase or decrease the volume of their devices. This innovation has the potential to revolutionize the way
people interact with their devices, making it more intuitive and convenient. In this project, we will explore the
development of gesture volume control technology. We will start by researching existing technologies and studying
their limitations. Then, we will use this knowledge to develop a new and improved system that overcomes these
limitations. We will use machine learning and computer vision techniques to detect and interpret hand gestures
accurately, allowing users to control the volume of their devices with ease. The project will involve designing and
building a prototype of the system and testing its functionality in real-world scenarios. We will also evaluate the
system's performance and identify areas for improvement. Ultimately, this project aims to contribute to the
advancement of gesture control technology, making it more accessible and user- friendly for everyone.
www.ijres.org 154 | Page
Gesture Volume Control
II. PROBLEM IDENTIFIED
Requires the Leap Motion Controller, which is a separate hardware device. The PyLeap Mouse module used for
simulating mouse clicks may not work on all systems. May not work well in low light conditions or with
cluttered backgrounds. The gesture recognition algorithm may not be robust enough to handle all types of gestures
accurately.
III. LITERATURE SURVEY
[1] A non-local algorithm for hand gestures was proposed by A. Buades, B. Coll, and
J. Morel. At the moment, finding finger movement algorithms remains a valid task. Functional analysis and
statistics collide. Despite the fact that most recently presented approaches have a high level of sophistication,
Algorithms have not yet reached a satisfactory degree of performance applicability. All work admirably when
the model matches the algorithm assumptions, but they all fail in general, producing defects in analyzing the
pixels through the camera. The primary goal of this study is to define a generic mathematical and experimental
technique for comparing and classifying conventional hand movement recognition algorithms. [2] For the no
required elements in the video frame, Golam Moktader Daiyan et al. (2012) suggested a high performance decision
based median filter. This technique detects noise pixels iteratively over numerous phases before replacing them
with the median value. Noise detection is accomplished by enlarging the field of view. Mask till 77% to keep
the extraction of local data going. Furthermore, if the algorithm fails to find a noise-free pixel at 7 7, the processing
pixel is replaced by the last processed pixel. If the noise-free median value isn't available in the 7th processing
window, the last processed pixel is used to determine if it is noise-free. The method chooses a window size if
the last processed pixel is noisy. Calculate the number of 0s and 255s in the processing window using the 1515
dimension. Then, in the selected window, replace the processed pixel with 0 or 255, whichever is higher in
number. [3] Rajeshwari Kumar Dewangan et.al accurate object information and obtain a location using a deep
learning object recognition technique. Object recognition algorithms are designed based on the Single Shot
Multi Box Detector (SSD) structure, an object recognition deep learning model, to detect objects using a camera.
[4] H. Jabnoun et, al suggested the system that restores a central function of the visual system which is the
identification of surrounding objects which is based on the local features extraction concept. Using SFIT
algorithm and keypoints matching showed good accuracy for detecting objects. [5] Košale U, Žnidaršic P, Stopar
K suggested that Detection of obstacles is performed by Time of Flight (ToF) sensors, whose ranging data is
then processed with an on-board microcontroller and send via Bluetooth connection to the belt. The belt is
equipped with a second microcontroller, which interprets the data and presents it to the wearer with 15 vibration
motors arranged in a square grid. The glasses are worn on the head, whereas the belt is attached around the
stomach area. But the number of sensors detecting the obstacle decreased with the distance. Circle and square
were detected better than triangle. This suggests that different shapes trigger different responses of sensors on
glasses.[6] In this paper, we have suggested a prototype of a robot based on “Human Gesture Recognition” with
Voice Recognition to control of a robot using gestures and voice, without any complication. The robot moves in
accordance with 3-axis accelerometer and a HC-05 Bluetooth module, which is the input device of the system
and captures the human hand gesture and voice recognition. The ADXL335 accelerometer is aro bust and easy
to use input device. It reduces the physical hardship of user and provide user with an ability and freedom to
maneuverer the robot in desired direction this goes same with the Bluetooth module also. Along with successfully
usingaccelerometer and the Bluetooth module in the robot, we have also employed ultrasonic sensors which
would help a user to detect any obstacle in his/her way and also provide the distance of obstacle from the robot.
In this age of technology where humans and machines are working together to take technology to the next level,
such type of prototype could play a vital role in various fields and pave the way for future generation.[7] We
proposed a robot prototype based on “Human Gesture Recognition” with Voice Recognition in the article to control
a robot using gestures and voice without any complications. The robot is controlled via a 3-axis gyroscope and an
ESP01 module, Which serves as the system’s input device and captures human hand gestures and voice
recognition. The gyroscope is a reliable and simple to operate input device. It decreases the user’s physical
exertion and gives them the ability and freedom to operate the robot in whatever direction they want. This is
also true of the WIFI module. In addition to successfully using the gyroscope and WIFI module in the robot, we
also used ultrasonic. Sensors that would assist a user in detecting any obstacles in his or her path as well as
providing the distance between the obstacle and the robot. In current age of technology, where humans and
robots collaborate to advance technology, such a prototype might be useful in a variety of disciplines and lead
the way for future generation.[8] Sign language is a useful tool to ease the communication between the deaf or
mute community and the normal people. Yet there is a communication barrier between these communities with
normal people. This project aims to lower the communication gap between the deaf or mute community and the
normal world. This project was meant to be a prototype to check the feasibility of recognizing sign language
using sensor gloves. With this project the deaf or mute people can use the gloves to perform sign language and it
will be converted in to speech so that normal people can easily understand. The main feature of this project is
www.ijres.org 155 | Page
Gesture Volume Control
that the gesture recognizer is a standalone system, which is applicable in daily life.[9] The robotic vehicle
can hence be controlled by voice and gesture which makes it more useful in this present pandemic situation.
This way we can reduce unnecessary human contact wherever possible, and we will also be able to control
without any fear of contact. There is also a high risk of spreading the virus by closely following the robotic
vehicle so by integrating with the Wi-Fi will have more range than the previously used Bluetooth module. This
would be of great help to reduce human presence in the areas such as health care facilities and quarantine
zones.[10] After several studies and survey around the world it have shown that both children and adults benefit
substantially from access to a means of independently move freely. Though many disabled people can satisfied
with traditional manual or powered wheelchairs, there is a category of disabled community find it difficult or
impossible to use wheelchairs independently. Many researchers have used several technologies to make a
wheelchair accessible to use for this population. Several wheelchairs have been developed with several control
devices. Our project was the complete combination of the electronic circuits, the hardware& software
knowledge. Automatic wheelchair can be used to handicapped people, especially those who are not able to
move. The system is successfully run to move the wheelchair left, Right, Forward, Backward or Stay in same
position.[11] The subject of this study is a robot that can be controlled via hand gestures and vocal instructions.
The robots can now be controlled via speech and gestures ,despite the fact that they were previously operated
manually. This gesture and speech recognition technology is defined by the interaction of the computer with
human body language. To build voice and gesture recognizer using speech and image processing along with
machine leaning models such that accuracy of the recognition is increased was primary goal. The project’s primary
purpose is to develop a robotic vehicle using Arduino and to control the vehicle using voice and gesture-based
information. Further to improve the robot’s overall security while also simplifying the control mechanism. The
robot can perform various operations such as start/stop, left/right, forward/backward movement. Also, many
industries are working on programming and operating robots using gestures and speech for various applications.
IV. EXISTING SYSTEM
Classical interactions tools like keyboard, mouse, touchscreen and etc., may limit the way we use the
system. All these systems require physical contact, in order to interact with system. Gestures can interpret same
functionality without physically interacting with the interfacing devices.
V. PROPOSED SYSTEM
Our proposed system aims on providing the service with no physical contact and only with the gesture
action. In the all existing system about volume gesture control is providing the volume control service using
only with the any one of thephysical contacts like arm band, remote and etc. In Our project we did not use any other
physical contacts to controls the volume. At first the user has to using the capture module. In thismodule is
responsible for capturing video from the user's camera. It will use OpenCV to access the camera andretrieve
frames from it. After that Handdetection module. In this This modulewill use the Mediapipe library to detectthe
user's hand in each frame. It will analyze the hand landmarks detected by Mediapipe to determine theposition of
the hand. After that Gesturerecognition module will analyze theposition of the hand detected by the hand
detection module to determine ifthe user is making a volume gesture. Itwill use NumPy to perform mathematical
operations on the hand landmarks data. Then Volume control module will use the Mediapipe libraryto detect the
user's hand in each frame.It will analyze the hand landmarks detected by Mediapipe to determinethe position of the
hand.
VI. DESIGN AND MODULES
6.1 Capture module:
Open CV is a library of python which tackle PC vision issue. It is used to detect the face which is done
using the machine learning. OpenCV provides a variety of functions to manipulate and analyze images and
videos, such as image filtering, transformation, edge detection, object detection, and tracking. This module is
responsible for capturing video from the user's camera. It will use OpenCV to access the camera and retrieve
frames from it.
6.2 Hand detection module:
MediaPipe is a library of python we used this module in our project to recognize the hand gesture and
detect the input from it. The main advantages of Mediapipe is its real-time performance. The framework is
designed to run efficiently on a variety of hardware platforms, including mobile devices and embedded systems,
making it idealfor developing applications that require low latency and high throughput.
6.3 Calculate The Distance:
NumPy is a Python library that provides support for large, multi-dimensional arrays and matrices, along with a
www.ijres.org 156 | Page
Gesture Volume Control
wide range of mathematical functions to operate on them. The library is designed to simplify the manipulation of
large datasets, and to provideefficient algorithms for numerical processing.
6.4 Volume control module:
This module will use the Pycaw library to control the system's volume based on the gesturerecognized by the
gesture recognition module. It will set the system's volumeto a specific value depending on the position of the
hand.
VII. ARCHITECHTURAL DESIGN
www.ijres.org 157 | Page
Gesture Volume Control
VIII. Results
www.ijres.org 158 | Page
Gesture Volume Control
IX. FUTURE SCOPE
The future scope of volume gesture control technology is promising. It has potential applications in
human-computer interaction and accessibility for people with disabilities. The technology can be used to
develop more potent links between humans and machines, rather than just the basic text user interfaces or
graphical user interfaces (GUIs). The technology can be further developed to recognize more complex hand
gestures and to control other device functions beyond volume control. For instance, a hand gesture recognition
and voice conversion system using has been proposed.
The technology can also be integrated with other machine learning libraries and audio control libraries
to improve its accuracy and functionality.
X. CONCLUSION
The development of gesture volume control technology is a promising area of research with significant
potential benefits for users. This technology provides an intuitive, convenient, and accessible way of adjusting the
volume of devices, which could improve the user experience and make devices more accessible to people with
disabilities. While there are several existing systems for gesture volume control, there is still room for
improvement in terms of accuracy, robustness, and user experience. Therefore, this project aims to contribute to
the advancement of gesture control technology by designing and building a prototype system that overcomes the
limitations of existing systems. By doing so, this project has the potential to make a significant contribution to
www.ijres.org 159 | Page
Gesture Volume Control
the field of human-computer interaction and could pave the way for more advanced forms ofgesture control in the
future.
REFERENCES
[1]. S. Rangarajan “Hand Gesture Recognitionusing OpenCV andPython”.
[2]. Nidhishree Arun, AnanyaDutta, V Namratha, BShreenivas “HandGesture Recognition and Volume Control”.
[3]. Parshav Maloo“Controlling Media Player with HandGestures”.
[4]. Jigmee Wangchuk Machangpaa, Tejbanta Singh Chingthamb“HeadGesture ControlledWheelchair forQuadriplegic Patients”.
[5]. Shadman Mahmood Khan Pathan, Wasif Ahmed, Md. MasudRana,Md. Shahjalal Tasin, Faisul Islam, Anika Sultana “Wireless Head
Gesture Controlled Robotic Wheel Chair for Physically Disable Persons”.
[6]. S.Kalaiarasi 1, Yash Trivedi 2, Sourav Banerjee 3, “Gesture ControlRobot using Accelerometer and Voice Control for the
Blind”.
[7]. Deekshith kumar, Harsha K C, Koushik D Kasolli, Yashwanth SuryaKumar, Prof.Rakesh Mallya “ Voice and gesture controlled
robot”.
[8]. Lavish Madaan, Amogh Bordwekar, A.N Srikanth, Prathamesh Konkar“Gesture to Voice Command Glove for Dumb”.
[9]. Gali Jeevan Sai1, V Siddharth Dhara2, K Sai Ragadeep “AutonomousVehicle for Supervision Based on Voice and Gesture Control”.
[10]. Prof. R.R.Bhambare1, Akash P. Ghaiwate2, Kishor B. Jadhav3, Hitesh K patil “Smart wheelchair control using voice and Gesture
control”.
[11]. H R Vanamala, Akash S M, Vinay A, Sanchit Kumar, MeghanaRathod “Gesture and Voice Controlled Robot for Industrial
Applications”.
www.ijres.org 160 | Page
