Scribd
Upload
98 views20 pages

Virtual Keyboard

The document presents a virtual keyboard implementation based on finger recognition. It describes the design of the virtual keyboard which uses a video camera and customized keyboard images as inputs. Two algorithms are used: one to extract fingertip positions and another to locate the virtual keyboard. An experiment tests the system under different lighting conditions, achieving an overall recognition rate of 94.62%. Future work aims to improve real-time performance and handle additional keyboard functions.

Uploaded by

Sowmya Kasoju
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
98 views20 pages

Virtual Keyboard

The document presents a virtual keyboard implementation based on finger recognition. It describes the design of the virtual keyboard which uses a video camera and customized keyboard images as inputs. Two algorithms are used: one to extract fingertip positions and another to locate the virtual keyboard. An experiment tests the system under different lighting conditions, achieving an overall recognition rate of 94.62%. Future work aims to improve real-time performance and handle additional keyboard functions.

Uploaded by

Sowmya Kasoju
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPT, PDF, TXT or read online on Scribd
You are on page 1/ 20

A

Presentation
On
Virtual Keyboard Implementation based on finger
recognition

Submitted by:-
AISHWARYA
16251A1231
2 CONTENTS

 Introduction
 Related work
 virtual keyboard design
 Experimental Algorithms
 Experimental testbed and data selection
 Experimental Results
 Conclusions and future work
 Limitations
 References

July 6, 202
1
3
INTRODUCTION

Keyboards remain as the most popular input


medium.
 Generally, keyboards are made up of some keys
and SCM
The concept of a virtual keyboard is that, it has the
same input and output functionalities as a traditional
mechanical keyboard.

July 6, 202
1
4 RELATED WORK

 Terajima developed a system that was capable of


using images captured by high-frame-rated camera.
 Overall, objective is to design fast finger tracking
system.
 Niikura developed in-air typing interface to remove
disadvantages of traditional keyboard.

July 6, 202
1
5
VIRTUAL KEYBOARD DESIGN

 The proposed virtual keyboard can be customized,it


will greatly improve the user experience.

 The input resources for the proposed framework is


 A.video camera
 B.customized keyboard

July 6, 202
1
6

 The two subsystems that are responsible for


processing the input customized keyboards and
videos are…
A)fingertip recognition and
B)the recognition of the customized keyboard

July 6, 202
1
A)FINGERTIP RECOGNITION
7

The BWMORPH algorithm for skeleton


extraction

July 6, 202
1
recognition of the customized
8
keyboard

July 6, 202
1
9 WORKING

July 6, 202
1
10 EXPERIMENTAL
ALGORITHMS

 The proposed algorithms used in the virtual


keyboard are to extract the fingertip position in
each frame(Algorithm I) and to locate the virtual
keyboard(Algorithm II)

July 6, 202
1
11 Algorithm I:Extract the Fingertip
Position in a Frame

July 6, 202
1
Algorithm II:Locate the Virtual
Keyboard.
13 EXPERIMENTAL TESTBED
AND DATA SELECTION
The adaptability of virtual keyboard were tested in
different environments.

July 6, 202
1
14
EXPERIMENTAL RESULTS

 The overall recognition rate of all inputs is 94.62%.


 The best average input recognition rate is at
97.7% from keyboard (a) under natural lighting
condition,
 and the worst case is 90.7% from keyboard (b)
under lamplight.

July 6, 202
1
15

July 6, 202
1
16 CONCLUSION

 Virtual keyboard can be printed on a plain paper or on a


wall or other flat surface.
 This can be placed on any plane.
 Users can expediently customize their own virtual
keyboard.

July 6, 202
1
17 FUTURE WORK

 The anticipated future improvements are :


(1) The virtual keyboard can work in real time;
(2) The prototype can identify two hands typing
simultaneously;
(3) It can work in dimly lit environments;
(4) Other function keys such as enter, delete, shift,
etc. can be added.

July 6, 202
1
18
LIMITATIONS

 One limitation of this approach is the need for


more sophisticated software.
 The small number of users used in this
feasibility study.

July 6, 202
1
19
References

 Athitsos, V., Wang, H., & Stefan, A. “A database-


based framework for gesture recognition”.
 Bérci, N., & Szolgay, P. “Towards a gesture based
human-machine interface: Fast 3D tracking of the
human fingers on high speed smart camera
computers”
 www.wikipedia.org

July 6, 202
1
20

THANK YOU

July 6, 202
1

You might also like