Journal of the ACS Advances in Computer Science

Volume 15, Issue 1, 2024

Virtual Keyboard-Mouse in Real-Time using Hand Gesture and Voice

Assistant
Dr/ Shaimaa Othman1, Dr/ Hany Maher Sayed Lala 2, Yosr Mansour1
1
Higher Institute of Computers and Information Technology, Computer Depart., El. Shorouk
Academy, Cairo, Egypt
2
Department of Mathematics, Faculty of Science, Al-Azhar, Cairo, Egypt
Email: [Link]@[Link], hmsayed@[Link] , [Link] @[Link]

Abstract
The advancement of computer applications has increasingly facilitated everyday tasks, with recent
innovations focusing on voice assistants and virtual input devices. This technology is particularly
beneficial for individuals with mobility challenges or in situations where direct manual computer
interaction is limited. Leveraging computer vision and artificial intelligence, these applications
can interpret visual data, such as human movements, and make decisions to execute corresponding
commands. This research incorporates a voice assistant, virtual mouse, and virtual keyboard to
enhance accessibility and usability, especially for individuals with physical disabilities or those
who prefer alternative input methods. Using Python, MediaPipe, and OpenCV, the application
effectively processes and interprets user gestures, providing a responsive and efficient computing
experience. MediaPipe’s features specifically contribute to the model’s precision, optimizing hand
tracking and gesture recognition for AI-driven tasks. Users can control the computer cursor
through various hand gestures, type on a virtual keyboard using colored caps or tapes and perform
essential actions like left-clicking and dragging items. This integrated solution aims to improve
productivity, making computers more accessible and enhancing the overall digital experience for
users. The fusion of AI and computer vision in such applications continues to drive forward
innovative and inclusive computing solutions, promising a future of greater accessibility and
convenience in human-computer interaction.

1. INTRODUCTION
In recent years, the subject of human-computer interaction has seen amazing advancements aimed
at improving the user experience and accessibility. The advent of smart technologies and natural user
interfaces has revolutionized how humans interact with machines. Traditional input devices, such as
keyboards and mice, while efficient, have limitations in dynamic environments requiring hands-free
operation or where physical space is constrained. These limitations have spurred the development of
innovative human-computer interaction (HCI) methods that leverage natural gestures and voice commands.
This research proposes a virtual keyboard-mouse system that combines real-time hand gesture recognition
with a voice assistant, creating a seamless, intuitive, and accessible interaction platform.

The primary motivation for this work stems from the increasing demand for more inclusive and adaptable
interaction solutions. Conventional input methods can be challenging for individuals with physical

1
DOI: 10.21608/ASC.2025.333048.1025
Virtual Keyboard-Mouse in Real-Time using Hand Gesture and Voice Assistant

disabilities or in environments where touch-free operations are critical, such as healthcare, manufacturing,
and remote work. Integrating gesture recognition and voice control offers a compelling alternative, enabling
users to interact with digital systems in a manner that feels natural and requires minimal learning. This can
lead to increased productivity, efficiency, and user satisfaction.
This research aims to explore developing a method for interacting with computers using hand gestures and
voice commands, by which the researchers hope to provide an inclusive and accessible computing
experience for a wider range of users.
By incorporating hand gestures and voice assistant technology, this research seeks to offer an alternative
and intuitive method of controlling computers and devices. Hand gestures can provide a natural and
expressive means of interaction, allowing users to perform various actions by simply moving their hands.
Moreover, integrating voice assistant capabilities enables users to issue commands and control devices
through voice commands, making the interaction process even more seamless and efficient.
Furthermore, the research paper aims to investigate the real-time capabilities of the proposed system. Real-
time interaction is crucial in various domains, such as gaming, virtual reality, and augmented reality. By
enabling real-time functionality, the researchers aim to enhance the user experience and enable seamless
integration of the virtual keyboard-mouse system into various applications and scenarios.
The objectives of this research are twofold. Firstly, to design and develop a virtual keyboard and mouse
system that can accurately interpret hand gestures and convert them into corresponding actions, such as
cursor movement and clicking. This requires the creation of algorithms and models capable of recognizing
and analyzing various hand gestures in real-time. Secondly, to integrate a voice assistant component that
can understand and execute voice commands related to device control. To achieve this, speech recognition
and natural language processing technologies must be implemented.
The motivations for the research on virtual keyboard-mouse using hand gesture and voice assistant revolve
around improving usability, accessibility, natural interaction, and real-time capabilities of human-computer
interaction. By addressing these motivations, the research aims to contribute to the advancement of human-
computer interaction technologies and provide users with a more intuitive and efficient way of interacting
with computers.
The rest of this paper is organized as follows: literature review is presented in Section 2. The system
implementation is explained in Section 3, and the results are discussed in Section 4. Finally, the conclusion
is drawn in Section 5.

2. LITERATURE REVIEW
Recently, interest in developing natural interactions between computers and humans has grown
significantly. Numerous studies have explored universal computing's human-computer interface.
Among these, the vision-based interface technique stands out for its ability to capture motion
information from video input without requiring costly equipment. Consequently, this method is
regarded as an effective tool for designing human-computer interfaces. This section conducts a
comprehensive review of existing literature, highlighting the transformative impact of AI on
computer-human interaction and its diverse applications.

2
Journal of the ACS Advances in Computer Science
Virtual Keyboard-Mouse in Real-Time using Hand Gesture and Voice Assistant

2.1 Hand gesture

Hand gestures are performed by making specific hand movements that are recognized by a hand
gesture recognition is typically done using computer vision techniques and machine learning
algorithms [16]. First, the hand region is detected and tracked in real-time video using computer
vision techniques like background subtraction, skin color segmentation, or a combination of both.
Many practical applications, such as virtual mice, remote controllers, sign-language recognition,
and immersive gaming technologies, use fingertip detection. Therefore, one of the primary
objectives of vision-based technology over the past few decades, particularly with conventional
red-green-blue (RGB) cameras, has been virtual mouse control via fingertip recognition from
pictures [1].
Numerous RGB-D sensor types, such the Kinect V2, or VicoVR [2], among others, can provide
body tracking. Among them, the low-cost, CPU-free Kinect V2 is becoming increasingly popular
these days. Convolutional neural network (CNN)-based RGB-D image-based systems have lately
demonstrated exceptional performance in HCI [3,4]. However, for model rendering and
assessment, these systems need high-performance CPUs and a bigger dataset.
Utilizing fingertip sensing and RGB-D pictures is considered a novel virtual mouse technique.
Without using a mouse, gloves, or markers, the user interacted with the computer by moving their
fingertip in front of a camera. The method showed off not just extremely precise gesture
estimations but also useful applications [1].
2.2 Gesture Recognition Techniques
Gesture recognition forms the backbone of virtual keyboards and virtual mice operated by hand
gestures [15]. Researchers have explored diverse methodologies, including computer vision and
deep learning algorithms, to enhance accuracy [17]. Noteworthy studies include Lin et al.’s work,
employing a combination of CNNs and LSTM networks for real-time hand gesture recognition
[6]. Similarly, Zhang et al. proposed a method that integrates depth information for precise gesture
recognition [5].
Shankar et al. have introduced two experiments. One involves controlling objects using hand
motions, while the other involves identifying the symbols we write in the air. In the first, a ground-
breaking method for manipulating the mouse cursor is introduced. By fusing motion modelling,
pattern recognition, and machine learning, this technique perfectly supports a range of mouse
movements. The second research explores air-writing recognition, a novel technique that involves
drawing letters and numbers by hand, in conjunction with the first [12].

2.3 Virtual Mouse using Hand Gestures

Virtual mouse systems, such as the one explored in the study [7], represent a significant leap in
HCI. By utilizing hand gestures, users can control the computer cursor intuitively. These systems
commonly employ depth-sensing cameras and machine learning algorithms. The research

3
Journal of the ACS Advances in Computer Science
Virtual Keyboard-Mouse in Real-Time using Hand Gesture and Voice Assistant

underscores the precision and responsiveness achieved by mapping hand gestures to cursor
movements, laying the foundation for seamless interaction.
Shetty et al. constructed a virtual mouse system using color detection [11].They used webcam for
detecting mouse cursor movement and click events using OpenCV built-in functions. A mouse
driver, written in java, is required as well. This system fails to perform well in rough background.
In the study [8], a method for hand gesture identification is presented, and computer vision
techniques are used to construct a virtual mouse and keyboard with hand gesture recognition. To
realistically control the computer, full keyboard functions, mouse pointer movement, and click
events are incorporated. All the inputs taken into consideration have their recognition and response
rates computed and shown in the findings. Comparing the accuracy of the proposed strategy to
other cutting-edge algorithms reveals that it performs better with a 95% accuracy.
A multidimensional approach to HCI may be seen in the convergence of hand gestures and voice
commands as shown in [9]. Users may interact with computers virtually by fusing several
modalities, which improves conventional user interfaces. The study emphasizes the connection
between movements and voice, demonstrating how subtle gestures combined with context-aware
voice instructions allow for complex and flexible interactions.
2.4 Virtual Keyboard using Hand Gestures
A finger recognition and gesture based augmented keyboard system is introduced in [13]. The
system was developed using OpenCV libraries and Python. Palm detection is used for typing on
the augmented keyboard. Virtual Keyboard performs based on the movement of the finger.
Phursule et al. developed an optical mouse and a virtual keyboard based on hand and face gestures
using computer vision. The system enables the computer’s mouse or pointer to move according to
gesture movements, with specific gestures performing right and left clicks. Additionally, various
gestures can execute keyboard functions. The project relies solely on a camera for hardware and
uses Python programming within the Anaconda platform [14].

3. SYSTEM IMPLEMENTATION
The aim of this paper is to implement a computer application that uses alternative methods of
keyboard and mouse cursor control for rehabilitation purposes, allowing stroke patients to recover
from. Therefore, we propose a new keyboard and mouse cursor control system based on visual and
color recognition techniques that utilize hand gestures recorded by a webcam. A system, which
incorporates cutting-edge computer vision, machine learning, and natural language processing
technologies. By interpreting hand gestures collected by a camera and processing spoken
commands through a voice assistant.
Modules partitions

4
Journal of the ACS Advances in Computer Science
Virtual Keyboard-Mouse in Real-Time using Hand Gesture and Voice Assistant

First, as we declared in the architecture of our project in Figure 1, we’ll be using Pyqt5 to design
and activate the interface of the application to make it usable on Desktop systems using Python
programming language.
The figure represents a system architecture for an integrated application that combines a voice
assistant, virtual keyboard, virtual mouse, and camera functionality, all within a Windows
application environment. The diagram outlines how these components interact with each other,
leveraging deep learning models and cloud-based platforms for enhanced functionality and
training.

Figure 1 project Architecture

The application implementation consists of two main modules Hand Gesture and Voice Assistant.
3.1 Hand Gesture Module:
Creating a virtual keyboard using hand gestures involves using computer vision techniques to
detect and recognize hand gestures in real-time. Using MediaPipe is an open-source framework
developed by Google that provides a comprehensive solution for building real-time multimedia
processing pipelines.

a. Capture Video Stream, Process Frames and Recognize Hand Gestures

In this step, you capture frames from the webcam, convert them to RGB (as MediaPipe requires
RGB input), and process the frames to detect hands using the MediaPipe Hands model.
b. BlazePalm Detector
• We train a palm detector instead of a hand detector to localize hand landmarks in real-time
from a single image or video frame.
• The model is based on a two-stage approach (hand region and hand landmarks)

5
Journal of the ACS Advances in Computer Science
Virtual Keyboard-Mouse in Real-Time using Hand Gesture and Voice Assistant

c. Hand Landmark Model

• After running palm detection over the whole image, our subsequent hand landmark model
performs precise landmark localization of 21.
• The model has three outputs.
o 21 hand landmarks
o A hand flag indicating the probability of hand presence in the input image.
o A binary classification of handedness, e.g., left, or right hand.
d. Recognize Gestures
In this step, you analyze the positions of hand landmarks to recognize specific gestures. Implement
the logic for recognizing gestures like thumbs up, peace sign, etc.

Figure 2 hand landmark

Following the successful development of our hand gesture recognition system, we implemented
this technology into four specialized sub-modules to enhance user interaction and control:

3.1.1 Virtual Keyboard algorithm

System must capture images via camera. The system provides the user with typing by hand
gestures such as the hardware keyboard. Here I used point number 12 to define an indicator and
point No. 8 and 7 in the action process.
• The system must allow the user to "click" on the key.
• The system must display the correct output for the key entered by the user.
• Functions provided by the system to the user:
I. Letters from A to Z
II. Numbers from 0 to 9
III. Enter button.
IV. Delete button.
V. Spacebar
VI. Capitalization

3.1.2 Virtual mouse algorithm

6
Journal of the ACS Advances in Computer Science
Virtual Keyboard-Mouse in Real-Time using Hand Gesture and Voice Assistant

• Use the camera to detect hand gestures through the 21 points on the hand.
• Know if the finger is closed (0) or open (1).
• By using points 8, 12, and 20, I can control the mouse.
• And control the action of the mouse by closing and opening points 8 and 12.
• The system provides control of the mouse by hand gestures and meets the needs of the user,
such as the hardware mouse.
• Functions provided by the system to the user:
i. Click on the left mouse button.
ii. Click on the right mouse button.
iii. Move the mouse pointer right, left, down and up That’s like a hardware mouse)

3.1.3 Media control player

• Use the camera to detect hand gestures through the 21 points on the hand.
• Stop Video by points 4, 8, 12, 16 and 20.
• Video Plus Five Sec by points 8
• Video Minus Five Sec by points 8, 12
• Increase video volume by points 8, 12 and 16
• decrease video volume by points 8, 12, 16 and 20
3.1.4 Scroll
• Uses gestures to facilitate scrolling through documents and web pages, providing a seamless
browsing experience.
• Using virtual mouse can be scroll in pc by points 8, 12 and 16.

3.2 Voice Assistant Module

• Allows access to the computer's mic when the user is talking.

• The user's voice is converted into text and processing is done, and then the required commands
are executed.
• The system must provide the user with the ability to carry out the command requested by the
user and talk to the computer by voice.
• Functions provided by the system:
a. Internet searches
b. Search inside the device for what the user wants, whether it is an audio file, video
or text.
c. Date >today-yesterday -last week -last year
d. Time
e. Weather
f. Open google &YouTube.
g. Write notes.
h. Weather state

7
Journal of the ACS Advances in Computer Science
Virtual Keyboard-Mouse in Real-Time using Hand Gesture and Voice Assistant

i. Send e-mails.

4. RESULTS & TESTING

In this paper, we comprehensively evaluated the performance and accuracy of various interactive
models, including a voice assistant, a virtual keyboard, and a virtual mouse model. Our testing
approach involved assessing a total of 15 voice assistant functions, each tested five times to ensure
consistency. Similarly, we evaluated the virtual keyboard input model's ability to recognize and
process commands for typing letters and numbers, along with control functions, with each function
undergoing ten trials. Additionally, we assessed the virtual mouse model's performance in
executing actions, also using ten trials for each function. Overall, our tests aimed to identify
strengths and areas for improvement in these models, ensuring their reliability and effectiveness
in practical applications.

4.1Voice assistant model test

This evaluation assessed voice assistant functions for accuracy, with core tasks like browser
navigation, date retrieval, and virtual device activation achieving 100% success. Weather updates,
speech-to-text, and note-taking functions performed well, though with slight inconsistencies,
resulting in an 80% accuracy. Email and file search functions were mostly accurate, with minor
issues in email generation. Overall, core functions excelled, while areas like speech recognition
need refinement.
Name of input output task [Link] Right percent
function trails output age
open_goo Voice No Open the google search 5 5 100 %
gle at the browser
open_yout Voice No Open the YouTube at the 5 5 100 %
ube browser
speak text Voice Turn the text into voice 5 4 80 %
today Voice Date (text) Give you the date of the 5 5 100 %
current day
yesterday Voice Date (text) Give you the date of the 5 5 100 %
previous day
last_year / Voice Date (text) Give you the date of the 5 5 100 %
last_week previous year /week from
the current day
time Voice time (text) Give you the time now 5 5 100 %
Weather Voice text Give you the temperature 5 4 80 %
degree and the state of
the weather now
search Voice no Search for the input text 5 5 100 %
on google engine and

8
Journal of the ACS Advances in Computer Science
 Virtual Keyboard-Mouse in Real-Time using Hand Gesture and Voice Assistant

display the results it in

the browser
rec_audio Voice text Turn the voice into text 5 4 80 %
Make_not Voice It takes a voice command 5 4 80 %
e and turn them into txt file
E_mail Voice and No It takes a voice 5 4 80 %
text (Voice commands and turn them
receiver) into email and send it to
specific user(receiver)
file email List of It searches in the whole 5 5 100 %
Voice (file matched hard desk to find the
that you files matched files
want to
find)
virtual_m Voice No It opens the virtual 5 5 100 %
ouse mouse program
virtual_ke Voice No It opens the virtual 5 5 100 %
yboard keyboard program
Table 1 Voice assistant test

4.2Virtual Keyboard model test

The Virtual Keyboard model test showed high accuracy across key functions. Capital letters, small
letters, and enter commands achieved 100% success, while numbers, backspace, caps lock, and
space functions demonstrated minor inconsistencies, scoring between 80-90%. Overall, the model
effectively performed core typing tasks with strong reliability.
Name of input output task Num of Right percent
function trails output age
Capital Video in real- A-Z Write Sentences 10 10 100%
Letters time
Small- Video in real- a-z Write Sentences 10 10 100%
Letters time
Numbers Video in real- 0-9 Write Numbers 10 8 80%
time
Backspace Video in real- Backspace Delete last 10 9 90%
time character
Caps lock Video in real- Caps lock Convert the letters 10 9 90%
time

9
Journal of the ACS Advances in Computer Science
 Virtual Keyboard-Mouse in Real-Time using Hand Gesture and Voice Assistant

Enter Video in real- Enter Press Enter Buttons 10 10 100%

time

Space Video in real- Space Make Space 10 9 90%

time
Table 2 Virtual Keyboard test

4.3Virtual Mouse model test

The Virtual Mouse model test demonstrated strong performance, with right-click, left-click, and
stop-pointer functions achieving 100% accuracy. Double-click, scroll, and pointer movement
functions showed minor inconsistencies, scoring between 80-90%. Overall, the model reliably
executed core mouse actions with high precision.
Name of Input output task Num of Right percentag
function trails output e
Right- Video in real- Right-Click Make Right click 10 10 100%
Click time
Left-Click Video in real- Left-Click Make Left Click 10 10 100%
time
Double- Video in real- Double-Click Make Double-Click 10 8 80%
Click time

Scroll-UP Video in real- Scroll-Up Make Scroll Up 10 9 90%

time In Files & PDF
Scroll- Video in real- Scroll-Down Make Scroll Down 10 9 90%
down time in Files & PDF

Stop- Video in real- NO Give you the date 10 10 100%

Pointer time of the per

Move- Video in real- Mouse Move Make the mouse 10 9 90%

Pointer time move

Table 3 Virtual Mouse test

5. CONCLUSION AND FUTURE WORK

This research proposed a cutting-edge framework for a real-time virtual keyboard and mouse
system that combines hand gesture recognition and voice assistant technology, offering an intuitive
and accessible method for HCI. The system employs computer vision for recognizing gestures and

10
Journal of the ACS Advances in Computer Science
Virtual Keyboard-Mouse in Real-Time using Hand Gesture and Voice Assistant

natural language processing to handle voice commands, ensuring smooth and effective user control
over digital interfaces.

The study outlined the primary motivations for this work, emphasizing the need for enhanced HCI
techniques and addressing the shortcomings of conventional input devices. The research focused
on developing a system that integrates gesture recognition with voice-based controls, aiming to
advance efficient and user-friendly interaction methods.

Experimental results demonstrated the system's remarkable accuracy in gesture recognition and its
prompt responsiveness to voice commands in diverse user scenarios. While the voice assistant
model performed well in its core functionalities, its speech recognition capabilities require further
enhancement. In comparison, the virtual keyboard model proved highly reliable for fundamental
typing tasks, and the virtual mouse consistently delivered precise execution of essential mouse
functions. These findings underscore the potential of multimodal input approaches to improve HCI
flexibility and accessibility.

The study's primary contribution lies in merging gesture and voice-based interaction into a unified
framework, overcoming the limitations of traditional input devices and single-modality systems.
By enabling hands-free operation and reducing dependence on physical hardware, this system
holds promise for applications in accessibility, gaming, virtual reality, and remote work.
Additionally, its real-time adaptability across diverse contexts offers valuable insights for
developers and researchers designing more intuitive and inclusive HCI systems.
Future research could expand this framework by exploring more complex gestures, multi-user
capabilities, and adaptive machine learning models to enhance scalability and accuracy. Further
advancements, such as integrating the system into wearable devices or augmented reality
platforms, could unlock novel real-world applications. Ultimately, this research contributes to the
evolution of HCI technologies, paving the way for a more inclusive and seamless digital
experience.

References
[1] Tran, DS., Ho, NH., Yang, HJ. et al. Real-time virtual mouse system using RGB-D images and
fingertip detection. Multimed Tools Appl 80, 10473–10490 (2021).
[2] Abhilash S S, Lisho Thomas, NWCC (2018) Virtual Mouse Using Hand Gesture. International
Research Journal of Engineering and Technology (IRJET)
[3]Jiang D, Li G, Sun Y, Kong J, Tao B (2019) Gesture recognition based on skeletonization
algorithm and CNN with ASL database. Multimed Tools Appl 78:29953–29970
[4] Ge L, Liang H, Yuan J, Thalmann D (2018) Robust 3D hand pose estimation from single depth
images using multi-view CNNs. IEEE Trans Image Process 27:4422–4436

11
Journal of the ACS Advances in Computer Science
Virtual Keyboard-Mouse in Real-Time using Hand Gesture and Voice Assistant

[5] Li Y, Zhang P. Static hand gesture recognition based on hierarchical decision and classification
of finger features. Sci Prog. 2022 Jan-Mar;105(1):368504221086362. doi:
10.1177/00368504221086362. PMID: 35296188; PMCID: PMC10358564.
[6] Guo, Lin & Zongxing, Lu & Yao, Ligang. (2021). Human-Machine Interaction Sensing
Technology Based on Hand Gesture Recognition: A Review. IEEE Transactions on Human-
Machine Systems. 51. 300-309. 10.1109/THMS.2021.3086003.
[7] R. Matlani, R. Dadlani, S. Dumbre, S. Mishra and A. Tewari, "Virtual Mouse using Hand
Gestures," 2021 International Conference on Technological Advancements and Innovations
(ICTAI), Tashkent, Uzbekistan, 2021, pp. 340-345, doi: 10.1109/ICTAI53825.2021.9673251.
[8] K. Aggarwal and A. Arora, "An Approach to Control the PC with Hand Gesture Recognition
using Computer Vision Technique," 2022 9th International Conference on Computing for
Sustainable Global Development (INDIACom), New Delhi, India, 2022, pp. 760-764, doi:
10.23919/INDIACom54597.2022.9763282.
[9] Sharma, M., Akilesh, G., Vishwaa, V. S., Sharon Femi, P., & Kala, A. (2022). Virtually
controlling computers using hand gesture and voice commands. Journal of Current Research in
Engineering and Science, 5(17).
[10] Gupta, D., Hossain, E., Hossain, M. S., Hossain, M. S., & Andersson, K. (2021). An
interactive computer system with gesture-based mouse and keyboard. In Intelligent Computing
and Optimization: Proceedings of the 3rd International Conference on Intelligent Computing and
Optimization 2020 (ICO 2020) (pp. 894-906). Springer International Publishing.
[11] Shetty, S., Yadav, S., Upadhyay, R., Bodade, V.: Virtual mouse using colour detection (2016)
[12] Shankar, A., Bondia, A., Rani, R., Jaiswal, G., & Sharma, A. (2024, January). Gesture-
Controlled Virtual Mouse and Finger Air Writing. In 2024 14th International Conference on Cloud
Computing, Data Science & Engineering (Confluence) (pp. 370-375). IEEE.
[13] Jagannathan, M. J., Surya, M., BT, A. M., & Poovaraghavan, R. J. (2018). Finger recognition
and gesture based augmented keyboard.
[14] Phursule, R. N., Kakade, G. Y., Koul, A., & Bhasin, S. (2023, August). Virtual Mouse and
Gesture Based Keyboard. In 2023 7th International Conference on Computing, Communication,
Control And Automation (ICCUBEA) (pp. 1-4). IEEE.
[15] Yadav, K. S., Anish Monsley, K., & Laskar, R. H. (2023). Gesture objects detection and
tracking for virtual text entry keyboard interface. Multimedia Tools and Applications, 82(4), 5317-
5342.
[16] Godbole, A., Gondke, V., & Devadkar, K. K. (2022, December). Hand Gesture Identification
and Voice Command Based Hardware Reduction. In 2022 IEEE Pune Section International
Conference (PuneCon) (pp. 1-6). IEEE.
[17] Patel, U., Rupani, S., Saini, V., & Tan, X. (2022, November). Gesture Recognition Using
MediaPipe for Online Realtime Gameplay. In 2022 IEEE/WIC/ACM International Joint
Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) (pp. 223-229). IEEE.

12
Journal of the ACS Advances in Computer Science