Group ID : CSE2016B47

HAND GESTURE RECOGNITION

VIRTUAL MOUSE

Submitted by: Submitted to:

Shivam Arya 1031230273 Mr. Sunil Kumar
Abhinav Chaturvedi 1031230312 Asst. Professor
Suraj Jindal 1031230327
Kushal Gupta 1031230320 SRM University

1/21
 Time Management
Requirement phase
Jan

Jan- Feb Analysis phase

Coding-
Feb- Mar Implementation
phase

Mar- April Testing phase

2/21
 CONTENT
• ABSTRACT
• INTRODUCTION
• PROJECT SCOPE
• GOAL & OBJECTIVE
• FEATURES
• PROBLEM STATEMENT
• LITERATURE SURVEY
• DESIGN
• DATA FLOW DIAGRAM
• UML DIAGRAM
• WORKING
• IMPLEMENTATION(SCREENSHOTS)
• REQUIREMENTS
• REFERENCES
3/21
 ABSTRACT
• A virtual mouse that is based on tracking the movement of
a finger is presented. The idea is for users to control their
computer or TV system simply by moving their fingers,
without any contact on realistic objects. A fast and robust
method that can trace the position of finger tip is proposed.

4/21
 INTRODUCTION
• There is no other more popular navigation/interaction device
than the mouse.
• Overcoming the restrictions a corporeal device has would enrich
the experience of interaction.
• Keeping this in mind, we present an idea of implementing a
virtual mouse system as an alternative.

Virtual Mouse is:

• User makes a specified hand gesture that is captured by a
camera.
• Object recognition techniques are used to extract information
from the capture.
• This is then translated to some meaningful event on the screen.

5/21
 PROJECT SCOPE
• Mouse is a physical device subject to mechanical wear and
tear.
• It is not easy to adapt to different environments and is
often limited by environment.
• Limited functions even in present operational
environments.
• For most laptop touchpad is not the most comfortable and
convenient.
• Virtual mouse, known as Virtual Multitask Mouse.
• This is real time application.
• User friendly application.
• This project removes the requirement of having a physical
device.

6/21
 GOAL AND OBJECTIVE

• The goal is to manage computers and other devices with

gestures rather than pointing and clicking a mouse or
touching a display directly.

• Studied the existing systems and available information to

understand.
• Main purpose – to eliminate physical constraints and add
adaptability.
• Reduce cost of hardware. 7/21
 FEATURES
Features of VIRTUAL MOUSE:
• Any new product should either make human life more
comfortable, more productive or more fun.
• Provides greater flexibility than the existing system.
• Can provide more functions depending on the choice of
object.
• Less prone to physical damage due to absence of a fixed
physical device.
• Avoid the mouse-related wrist damage like CTS & RSI.
• Also, there is a certain degree of fun & entertainment
associated with the whole idea.

8/21
 PROBLEM STATEMENT
• To design virtual mouse which detects hand gestures
patterns instead of physical mouse.
• Basically we use fingertips or colored tips for detection
which are captured by webcam.
• Here, the fingertip acts as an object which the web cam
senses.
• The camera is positioned such that it recognizes the
moment of finger tips and performs the operations of
mouse.
• The utilization of virtual mouse appears in space saving
situations or in movement situation.
9/21
 Literature Survey
• HCI Technology
Human-computer interaction (HCI) is an area of
research and practice that emerged in the early 1980s.
• Gesture Recognition
Gesture recognition is the mathematical interpretation of
a human motion by a computing device.
Using Palm Using Glove

10/21
 Design

Image Object Trace

Acquisition Recognition Object

Setting
Event Coordinate
Cursor
Generation calculation
Position
11/21
Data Flow Diagram

Input Image Image Resize Segmentation

Compute
Center Denoise

Get finger Control

Get Radius
Tips mouse

12/21
UML Diagram Image acquisition

Object Recognition

Virtual Mouse Trace Object

Calculate coordinate
Output

Actor Get fingertip

Event Generation

13/21
WORKING

1.Image Resize
• Map camera coordinates to screen
coordinates.

2.Segmentation
• Separate the hand area from a complex
background.
• we converted from RGB color space to
YCbCr color space, and then to binary
image.

14/21
WORKING (contd.)
3.Denoise
• Need to delete noisy pixels from
the image.
• We use an image morphology
algorithm that performs image
erosion and image dilation to
eliminate noise .
• Erosion trims down the image area
where the hand is not present .
• Dilation expands the area of the
Image pixels which are not eroded.

15/21
WORKING (contd.)
4.Finding center and the size
of the hand
• Locate the center of the hand,
we compute the radius of the
palm region to get hand size.
• Draw a circle increasing the
radius of the circle from the
center coordinate until the
circle meets the first black pixel.
• When the algorithm finds the
first black pixel then it returns
to the current radius value.

16/21
IMPLEMENTATION (SCREENSHOT)

17/21
IMPLEMENTATION (SCREENSHOT)

18/21
IMPLEMENTATION (SCREENSHOT)

19/21
 HARDWARE & SOFTWARE
REQUIREMENT
• Web Cam

• C is one of the programming languages designed for the

Common Language Infrastructure.
• OpenCV (Open Source Computer Vision Library) is a
library of programming functions mainly aimed at real-
time computer vision, developed by Intel.
• OpenCV runs on Windows, Android, iOS, Linux and Mac
OS.

20/21
 REFERENCES
[ 1 ] A. Erdem, E. Yardimci, Y. Atalay, V. Cetin, “Computer vision
based mouse”, Acoustics, Speech, and Signal Processing, 2002.
Proceedings. (ICASS). IEEE International Conference.
[2] Robertson P., Laddaga R., Van Kleek M,” Virtual mouse vision
based interface”, 2004.
[3] Vision based Men-Machine Interaction
http://www.ceng.metu.edu.tr/~vbi/
[4] Chu-Feng Lien, “Portable Vision-Based HCI - A Real-time Hand
Mouse System on Handheld Devices”
[5] Asanterabi Malima, Erol Ozgur, and Mujdat Cetin,” A Fast
Algorithm for Vision-Based Hand Gesture Recognition for RobotControl”

21/21