|Title:||Biometric person authentication with video-based eye tracking|
|Subject:||Hong Kong Polytechnic University -- Dissertations|
Identification -- Automation
|Department:||Faculty of Engineering|
|Pages:||63 leaves : col. ill. ; 30 cm.|
|Abstract:||Biometric authentication methods have been widely studied in recent years. Different physiological and behavioral traits are explored to perform person authentication, such as hand/finger images, facial characteristics, iris patterns, signatures, audio, and so on. In this dissertation, we present a new biometric authentication method, video-based eye tracking biometric authentication. An attention-catching video is designed to track how people pursue moving objects with an eye tracker. Various properties of eye tracking data, including acceleration, geometric, and muscle characteristics, are studied and extracted for biometric person authentication. In total, 34 features are extracted from the eye tracking data and evaluated by a feature selection algorithm. To achieve more efficient biometric authentication, the most discriminative features selected from the 34 features based on the feature evaluation are used to represent the physiological/behavior characteristics of human subjects. Finally, two different classifiers, Back Propagation (BP) Neural Network and Support Vector Machine (SVM), are trained to perform person authentication. Experimental results show that eleven selected physiological/behavior features achieve the best authentication performance of 82% correct rate by using the SVM classifier.|
|Rights:||All rights reserved|
Files in This Item:
|b24158033.pdf||For All Users (off-campus access for PolyU Staff & Students only)||1.38 MB||Adobe PDF||View/Open|
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item: