This document summarizes a student project to develop a gesture controlled virtual mouse. The objectives are to manage computers and other devices with gestures to reduce hardware costs and make complex tasks like 3D modeling easier. The technologies used include Python, OpenCV for computer vision and hand landmark detection. The methodology involves detecting the user's hand gestures like fingers up/down to move and click the cursor, scroll, control volume and brightness. A literature review showed existing systems have limitations like difficulty with backgrounds and skin tones. The proposed system aims to overcome these through improved recognition of patterns regardless of skin tone or backgrounds.
Technologies Used
All theoperations can be virtually controlled by using static and dynamic hand
gestures.
The technologies used are –
• Python 3.11.0
It is a High level ,General purpose programming language .
• OpenCV – 4.5.5
OpenCV is a Python open-source library, which is used for computer vision in Artificial
intelligence, Machine Learning, face recognition.
12.
Methodology
Operations on cursor
•Hand Landmark Detection (fingers up(1) and down(0))
• Move
• Left click
• Double click
• Right click
• Scroll Up
• Scroll Down
• Volume control
• Brightness control
Steps-
• It will detect the camera, video interface will be start.
• The camera can extract and recognize human hand gestures from video interface
• Hand tracking functionality is done by media pipe.
• After the recognition the cursor move accordingly, to perform various operation.
13.
Serial
no.
Name of theresearch paper and author Advantages
1
Virtual Mouse using object tracking 2020 by
Cristina Daniel, Monali Shetty
Accuracy of the system in
plain background Is 90%
2
Virtual mouse implementation using open cv 2019
by Dr.Prern Jacob
Used python for hand
gesture recognition
3
Hand gesture virtual mouse for human computer
interaction 2018 by Sherin Mohammad
Get 90% correct detection
for both views, under the
enough light conditions.
Literature Review
14.
Existing Proposed
V/S
Existing Consistof simple mouse
application using coloured tips for
detection which are captured by
Web-Cam, difficulty in finding the
hand gestures due to background
noise
The System works by Identifying
the colour of hands and decides
the position of cursor, System can
work for skin tone of any colour
Angle Between Fingers
Background Noise
Skin tone can bother
Limited features
Recognize Patterns
Overcome Background Noise
Works for any skin tone
Number of features
15.
FutureEnhancement
• It dependson the needs and intrests of the user.
• We are going to more feature such as
-Face regonition
-object detection
-video editing
-speech recognition
• Improved performance
16.
References
• Abhilash S.S.,LishoThomas,Naveen Wilson,Chaitnya C “virtual Mouse Using
Virtual Mouse”, International Research Journal of Engineering and Technology
(IRJET) Volume:05 Issue :04|Apr_2018
• Anandi Mishra,Sultan Faiji,Pragati Verma ,Shyam Dwiwedi,Rita Pal “Virtual
Mouse Using Hand Gesture”,Journal of Emerging Techonologies and
Research(JETIR) 2022 JETIR April 2022,Volume 9.
• Viral Doshi,Nishiket Bidawat,Ankit sharma,Parth Sakariya “Gesture Controlled
Virtual Mouse”.
17.
• We aredeveloping a system to control the mouse cursor using a real
time Camera.
• This system is based on a computer vision algorithms and can do all
Mouse tasks.
• However it enables to get stable results cause by the variety of lighting
and skin colours of human races.
• This system could be useful in presentations and to reduce work.
• Features such as enlarging and shrinking windows, closing window etc.
By using palm and multiple fingers.
Conclusion