Eye Blink Controlled Virtual Keyboard Using

Brain Sense & Raspberry Pi

ABSTRACT

• In our society there are more people suffered by paralytic diseases

causes them several disabilities like they are unable to talk and
unable to move physically and unable to express their everyday basic
needs, but they can still use their eyes and sometimes move their
heads. This Project is working under the principle of Brain-Computer
Interface (BCI)
• Our model helps them to type the letters using virtual keyboard,
which is displayed in the monitor, designed using python
programming. This system is having core system as Raspberry Pi.
Virtual keyboard contains alphabets, numbers and some punctuation.
Mouse pointer gets automatically shifted through every key,
characters can be chosen by making an eye blink at particular
position of mouse pointer at certain character.
INTRODUCTION

• The Brain-Computer Interface (BCI) is one of the communication channel used to

make an interaction between the human brain and a digital computer. BCI which
monitors EEG waves from the Brain. EEG –Electroencephalography which
monitors an Electrical property of the Brain along with the Scalp (Non-invasive).
The Neurosky Mindwave mobile / BrainSense measures intentionally directed
EMG activity (blink strength).   A brain-computer interface (BCI) is a new
communication channel between the human brain and a digital computer. The
ambitious goal of a BCI is finally the restoration of movements, communication
and environmental control for handicapped people
• The Raspberry Pi is a credit card sized single computer or SoC uses ARM1176JZF-
S core. SoC, or System on a Chip, is a method of placing all necessary electronics
for running a computer on a single chip. Raspberry Pi needs an Operating system to
start up. In the aim of cost reduction, the Raspberry Pi omits any onboard non-
volatile memory used to store the bootloaders, Linux Kernels and file systems as
seen in more traditional embedded systems. Rather, an SD/MMC card slot is
provided for this purpose. After boot load, as per the application program,
Raspberry Pi will get executed.
SNO TITLE YEAR AUTHOR CONCEPT TECHNIQUE FUTURE DRAWBACKS
SCOPE
1 Brain Computer 2015 A. This work presents the development Brain The developed Multi
of a Brain Computer Interface (BCI) SSVEP BCI
Interface based on González- based on Steady State Visual Evoked computer electrode
SSVEP for Mendoza, J. Interface - BCI might have sensor hence
Potentials (SSVEP), that enables a
many uses
Controlling a L. Pérez- user to control a remote control car. Electro such as control the cost is
The visual stimulus conditions of
Remote Control Benítez , J. area, frequency, and shape were encephalogra of wheel high
Car. A. Pérez- evaluated with the purpose of phy – EEG chairs, or even
Benítez , obtaining the SSVEP signal with the Steady State the control of a
highest amplitude in order to obtain car, or an
J.H. Espina- the best performance of the Visual Evoked
Hernández. developed BCI. A remote control car Potential – interaction
was built and was controlled by a with a
healthy subject using the developed
SSVEP. computer with
SSVEP BCI, proving its proper the purpose of
functionality. helping people
with motor
disabilities.

2 EEG-based Hybrid 2017 Yuanqing In this paper, we presented two Multidimentio Clinical Slow interace
hybrid brain computer interfaces
BCIs and Their Li, Tianyou (BCIs), one combing motor imagery nal control; applications,
Applications Yu (MI) and P300 and another combing P300; motor e.g.,
P300 and steady state visual evoked imagery;Stead detection of
potential (SSVEP), and their
applications. An important issue in y state visual residual
BCI research is multidimensional evoked cognitive
control. Potential applications potential, function and
include BCI controlled computer
mouse, document and email awareness covert
processing, web browser, wheelchair detection. awareness in
and neuroprosthesis. The challenge patients with
for EEG-based multidimensional
control is to obtain multiple disorders of
independent control signals from consciousnes
the noisy EEG data. s have
validated its
superior
performance
.
SNO TITLE YEAR AUTHOR CONCEPT TECHNIQUE FUTURE DRAWBACKS
SCOPE

3 EEG Artefacts 2019 Aysa One of the main issues restricting

the practical efficiency of brain-
Electroence Smart Needs an
Handling in a Real phalography portable android
Practical Brain–
Jafarifar computer interface (BCI) systems is
assistant device
mand
the inevitable occurrence of ,
Computer physiological artefacts during system
Interface electroencephalography (EEG) Automobiles
recordings. The effects of the
Controlled Vehicle artefacts are, however, mostly ,
discarded in practical BCI systems, Feature
due to the time-consuming and
complicated computational extraction,
processes. This paper presents the Adaptive
influences of the artefacts and the
efficiency of reducing these filters,
influences in a practical BCI. Ocular Correlation,
and muscular artefacts are
considered due to the high- Signal
amplitude and frequent presence. processing
algorithms

4 Single Versus 2016 Alex This work aimed to find and evaluate
a new method for detecting errors in
Brain– With this new s. If the
Multiple Events Kreilinger∗ computer technique of direction is not
continuous brain–computer interface
Error Potential , Hannah (BCI) applications. Instead of interface combining MEs intentional for a
classifying errors on a single-trial for error time, the ErrPs
Detection in a BCI- Hiebel, and basis, the new method was based on (BCI), detection, accumulated by
Controlled Car Gernot R. multiple events (MEs) analysis to continuous otherwise the discrete
Game With Muller-Putz increase the accuracy of error
detection. Methods: In a BCI-driven
feedback, unused events could be
Continuous and car game, based on motor imagery electroenceph applications used as a safety
Discrete Feedback (MI), discrete events were triggered alogram might regain mechanism to
whenever subjects collided with coins
(EEG), error interest if their stop the
and/or barriers. Coins counted as performance movement or to
correct events, whereas barriers were potential can be alter its
errors. (ErrP). improved to direction.
permit
reasonable
functionality.
SNO TITLE YEAR AUTHOR CONCEPT TECHNIQUE FUTURE DRAWBACKS
SCOPE

5 Neuro Based 2018 Various types of therapy EEG; This neuro- Involves high
Racing Car for N. H. have been introduced to Attention based level data
Cognitive Training Azman, lower the number of Deficit physical processing
W. Mansor, children with Attention Disorder; game is need to use
Khuan Y. Deficit Disorder (ADD). neuro suitable for costly
Lee1 Some available treatments feedback; ADD children hardware
are not suitable for the attention and can be
children since medication level; used to train
is used and requires them microcontroll them to
to meditate. The use of er; brainwave; perform
Neuro based physical brain- tasks with
game to perform cognitive computer full
training on ADD children interface; concentratio
has not been reported. embedded n.
system.
EXISTING SYSTEM

In the existing system, every application is developed using

Matlab, it requires a computer for processing signal and
processing application through Matlab.
PROPOSED SYSTEM

Since the system uses Raspberry Pi, it does not require Matlab
for processing the signal. Raspberry pi which has in built
Bluetooth, so that there is no need of external Bluetooth. In this
proposed system virtual keyboard is designed using python
programming by having Tkinter library for virtual keyboard
design and Pyautogui library for mouse pointer movement.
BLOCK DIAGRAM
BLOCK DIAGRAM DESCRIPTION

• Since, Raspberry Pi is small Pc, It is having option to connect

monitor. Raspberry pi contains HDMI port; monitor can be
connected by using VGA to HDMI convertor cable.
Brainsense is connected with Raspberry pi using Bluetooth.
Virtual keyboard, which is created using python programming,
got displayed in the Monitor.
HARDWARE REQUIRED

• Raspberry Pi
• Mindwave mobile or Brain sense
• Home automation kit (Appliances and Relay)
Raspberry Pi Model
B
 Raspberry Pi 3
The Raspberry Pi 3 Model B is the third generation
Raspberry Pi. This powerful credit-card sized single
board computer can be used for many applications
and supersedes the original Raspberry Pi Model B+
and Raspberry Pi 2 Model B. Whilst maintaining the
popular board format the Raspberry Pi 3 Model B
brings you a more powerful processer, 10x faster than
the first generation Raspberry Pi. Additionally it adds
wireless LAN & Bluetooth connectivity making it the
ideal solution for powerful connected designs.
 Specifications
Processor
Broadcom BCM2387 chipset.
1.2GHz Quad-Core ARM Cortex-A53
802.11 b/g/n Wireless LAN and Bluetooth 4.1 (Bluetooth Classic and
LE)
GPU
Dual Core VideoCore IV® Multimedia Co-Processor. Provides Open
GL
ES 2.0, hardware-accelerated OpenVG, and 1080p30 H.264 high-
profile
decode. Capable of 1Gpixel/s, 1.5Gtexel/s or 24GFLOPs with texture
filtering and DMA infrastructure
Memory
1GB LPDDR2
Operating System
Boots from Micro SD card, running a version of the
Linux operating system or
Windows 10 IoT
Dimensions
85 x 56 x 17mm
Power Micro
USB socket 5V1, 2.5A
SOFTWARE REQUIRED

• Raspbian OS
• SD card Formatter
• Win32 disk imager