I=
Pakistan Research Repository Home
 

Title of Thesis

Efficient Correlation Algorithm for Gaze Direction & Head Gesture

Author(s)

Tabassam Nawaz

Institute/University/Department Details
Department of Computer Engineering / University of Engineering and Technology, Taxila
Session
2008
Subject
Computer Science
Number of Pages
71
Keywords (Extracted from title, table of contents and abstract of thesis)
Estimation, Efficient, Environment, Gesture, Regression, Device, Direction, Detection, Head, Gaze, Algorithm, Solution, Correlation

Abstract
The aim of this thesis is to explore new applications in the area of human computer interaction and to propose solution for these applications based upon gaze direction and head gesture. Gaze direction and head gesture are considered as input modalities for human computer interaction with different degree of freedom and different capabilities.
Gaze direction estimation is achieved by subsequent stages: face detection, eye detection, eye gaze estimation and coordinate mapping for interaction of gaze over natural world surface. Face detection has been achieved by adaboost which combine visual critical feature based weak learner and produce a strong classifier.Assumingly face is detected, and then eyes are detected based upon texture feature. A regression neural network based gaze interaction with a surface is proposed.The regression neural network is trained over eye image while gazing in several directions. Accuracy of the proposed system is based upon the performance of this regression neural network that has to produce the coordinate which are being gazed by human eye.The detected eye gaze is further
correlated with head gesture: head shake and head node to provide interaction mechanism with the real world. Practical performance of the system was tested in different real world environment such as infotainment device control and in automotive.The dissertation also proposes two novel applications in the area of augmented reality based upon gaze direction and head gesture. Augmented reality is combination of real world and computer generated data.A subset of gaze direction is proposed in which head orientation is considered and gross level gaze direction is proposed. This gross level gaze defines current field of view which is then animated and useful information is displayed for situation aware environments.

Download Full Thesis
1,642 KB
S. No. Chapter Title of the Chapters Page Size (KB)
1 0 CONTENTS

 

 
29 KB
2

1

INTRODUCTION

1.1 Problem statement
1.2 Description

1
107 KB
3 2 FACE DETECTION AND HEAD GESTURE RECOGNITION

2.1 Introduction to Face Detection
2.2 Research challenges in Face Detection
2.2.1 Benchmark Face Databases
2.3 Proposed Methodologies
2.4 Introduction to Gesture Recognition
2.5 Architecture of Gesture Recognition System
2.6 Application Domain of Gestures

6
329 KB
4 3 EYE GAZE

3.1 Introduction
3.2 Eye Gaze Applications
3.3 Eye Gaze Estimation

24
291 KB
5

4

INFOTAINMENT DEVICES CONTROL BY EYE GAZE AND GESTURE RECOGNITION FUSION

4.1 Introduction
4.2 Real Time Gesture and Gaze Direction Based Virtual Infotainment Control System
4.3 Algorithm Design
4.4 Conclusion

29
405 KB
6

5

EXPERIMENTAL SETUP AND RESULTS

5.1 Development Environment & Results
5.2 Results

48
309 KB
7

6

NOVEL AUGMENTED REALITY APPLICATIONS BY EYE GAZE AND HEAD GESTURE

6.1 Introduction
6.2 Augmented Reality Application for Automotive
6.3 Proposed Architecture

92
264 KB
8

7

CONCLUSION AND FUTURE WORK

7.1 Conclusion
7.2 Future Work

55
190 KB