Rutuja Magar et al IJSRE Volume 4 Issue 12 December 2016 Page 6108 Volume||4||Issue||12||December-2016||Pages-6108-6112||ISSN(e):2321-7545 Website: http://ijsae.in
DOI: http://dx.doi.org/10.18535/ijsre/v4i12.06
“Eye Movement Detection Algorithm for Wheelchair”
Authors
Rutuja Magar1, Karishma Pawar2, Pooja Derle3, Vishakha Sangle4 Computer Department/ SPPU University, Nashik, India
[email protected] ABSTRACT:
A wheel chair is a device for physically challenged persons to move wheel chair in any desirable direction using eyeball. In order to take care for different disabilities,various kinds of techniques,methods,algorithms are developed.The proposed model is a alternative for those methods.The proposed method consists of hardware and software which eliminates the person’s work using eyeball sensor. User’s eye movement are capture from web camera,then computer input system will send command to the software based on the angle of rotation of pupil. like joystick we can map eye movement to control wheelchair movements.The final part of the project is the design of wheelchair.All four Wheels connected to Arduino microprocessor that will send signals to motor Drivers.
Index Terms- IR sensor, Arduino Micro-controller, DC Motor, Eyeball Sensor
I. INTRODUCTION
It is difficult for a physically challenged person to move wheelchair in any desirable using hand or legs. The image processing is used to detect eye location and eye movement at the back end.In this proposed system the video capturing helps to start tracking eye movement.i.e when user moves his eye balls up (move forward),left (move left),right(move right) in other cases wheel chair will stop. An electric wheelchair will moved with DC Motor using eye movement detection algorithm for wheelchair.The most challenging aspects is detection of iris and pupil location determining the eye’s movement and controlling the wheelchair’s in proper movement using Eyeball. Once the image has been processed it moves into the second part,then the image is converted into gray scale.Also the Arduino and the object detection sensors will be connected to microprocessor to provide necessary feedback for proper movement of the wheelchair.At the last of this proposed there is wheelchair control unit this converts eye location information.
II. LITERATURE SURVEY
Till today various work done on automated wheelchair. But they have their own limitations.
In [1]“Automatic wheelchair using eyeball sensor” The touch screen method is used as input device and it is connected to user’s gesture. An IR obstacle detection unit was used which is fixed to the wheelchair to avoid possible accident.
Rutuja Magar et al IJSRE Volume 4 Issue 12 December 2016 Page 6109 III. SYSTEM ARCHITECTURE
An eye tracking system measures the point of gaze by analyzing eye movement.[3] It is mostly used in commercial servicces.Ardunino is an open source.An input could be digital or analog and could come the environment or a user.
.
Figure 1. Block Diagram of the Project
An important concept is that of the resolution of the system, which is the smallest eye movement which can be reliably detected. Eye tracking system typically use the relation between the corneal reflection, and the center of the pupil to identify gaze detection[3]
1. Hardware Implementation HD Web Camera
Arduino micro-controller board LCD display
Motor Driver Relay Board DC motors.
2 . Software Implementation Operating System: Windows 7 + IDE: Visual Studio 2010
Framework: .Net Framework 4
IV. IMAGE PROCESSING
Rutuja Magar et al IJSRE Volume 4 Issue 12 December 2016 Page 6110 Method:
Cv Capture cap=CvCapture.FromCamera(1);
Make the image invert
Method :
Invert a = new Invert(); aq= a.Apply(aq);
AForge.Imaging.Image.FormatImage(ref aq); 3. Convert it into Grayscale
Method :
IFilterfilter=Grayscale.CommonAlgorithms.BT709; aq = filter.Apply(aq);
4. Convert the image into binary image using threshold value 220
h = fil2.Apply(aq).Height;
.Threshold th = new Threshold(220); aq = th.Apply(aq);
Rutuja Magar et al IJSRE Volume 4 Issue 12 December 2016 Page 6111 BlobCounterbl = new BlobCounter(aq);
int i = bl.ObjectsCount;
ExtractBiggestBlob fil2 = new ExtractBiggestBlob(); fil2.Apply(aq);
6. Find centre position of biggest object as eye position.
int x = 0; int y = 0; int h = 0; if (i >0) {
fil2.Apply(aq);
x = fil2.BlobPosition.X; y = fil2.BlobPosition.Y; h = fil2.Apply(aq).Height; }
7.Determine object’s center point and height i.e center(x,y)
8.Determine object’s center point position using y co-ordinate (a)If up_y_min<y<up_y_max is true then eye is in top position i)If up_x_min<x<up_x_max then eye is in up position
else
invalid position
(b)If right_y_min<y<right_y_max is true then eye is in middle position i)If right_x_min<x<right_x_max then eye is in right position
ii)else If left_x_min<x<left_x_max then eye is in left position
iii)elseIf center_x_min<x<center_x_max then eye is in center position iv)else eye is in invalid position
(c) Else eye is in bottom position
i) If down_x_min<x<down_x_max then eye is in down position else eye is in invalid position
step 9.Draw position of eye on picture step 10.End
Rutuja Magar et al IJSRE Volume 4 Issue 12 December 2016 Page 6112 V. CONCLUSION
The proposed model is designed for physically challenged person which is very simple and cost effective and easy to operate.At the last of this proposed system there is wheel chair control unit this unit converts eye location information into hardware commands to control wheelchair.It also Contain Arduino board which is very useful to handle and simple to implement.
VI.REFERENCES
1. Rajavenkatesan, Nagalakshmi, Ram Prasath.K, Venkataramanan.“AUTOMATIC WHEELCHAIR USING EYEBALL SENSOR” International Journal of Advanced Technology in Engineering and Science Volume No 03, Special Issue No. 01, March 2015
2. Monika Jain, Shikhar Puri, Shivali Unishree “ Eyeball Motion Controlled Wheelchair Using IR Sensors” World Academy of Science, Engineering and Technology International Journal of Computer, Electrical, Automation, Control and Information Engineering Vol:9, No:4, 2015