Download presentation
Presentation is loading. Please wait.
1
Moving The Mouse Pointer Using Eye Gazing
Student: Ibraheem Frieslaar Supervisor: Mehrdad Ghaziasgar
2
OVERVIEW INTRODUCTION USER INTERFACE SPECIFICATION HIGH LEVEL DESIGN
LOW LEVEL DESIGN DEMO REFERENCES QUESTIONS & ANSWERS
3
INTRODUCTION Eye ball tracker
Using the webcam to determine eye gaze location Moving the mouse to that location
4
USER INTERFACE SPECIFICATION
Runs in the Background It’s a Daemon
5
High Level Design Input Webcam Image Processing Move Mouse Pointer
6
Low Level Design Input Webcam Image Processing Move Mouse Pointer
Haar Detection Locate Eyes Determine left Eye Locate Iris SVM
7
Low Level Design Input Webcam Acquire Image cvQueryFrame( capture )
8
Low Level Design Haar Detection Haar like features Detects Eyes
cvHaarDetectObjects
9
Low Level Design Locate Eyes Set Haar Detection as Region of Intrest
cvSetImageROI Determine left Eye Half the image for left eye cvSetImageROI/2
10
Low Level Design Locate Iris Hough Circles Determine Darkest Pixels
circles = cvHoughCircles Display Circle DarkPixels = DarkPixels + (255-s.val[0]) MaxDarkPixels = DarkPixels cvCircle
11
Low Level Design Right Eye Eye Redrawn SVM Pixel values saved
Values sent to Support Vector Machine (SVM) 1 1:255 2:255 3:255 4:0 5:0 6:0 7:255 8:255 system("svm-predict.exe Test trainer.model result") SVM Prediction
12
Low Level Design Move Mouse Pointer SetCursorPos(x,y);
13
Demo
14
REFERENCES OpenCVWiki. lOpenCVWiki. [Online]. Heiko Drewes, "Eye Gaze Tracking for Human Computer Interaction," Ludwig-Maximilians-Universität, Munich, 2010.
15
QUESTIONS AND ANSWERS Thank You!
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.