Home // IMMM 2012, The Second International Conference on Advances in Information Mining and Management // View article

On Biometric Verification of a User by Means of Eye Movement Data Mining

Authors:
Youming Zhang
Martti Juhola

Keywords: biometric verification; eye movements; saccades; multilayer percetron neural networks; radial basis function networks; support vector machines; logistic discriminant analysis

Abstract:
In biometric verification, a signal, image or other dataset is measured from a subject to detect him or her to be or not to be an authenticated subject such as the user of a computer. So far, biometric verification has mainly been on the basis of fingerprints or face images, infrequently other images, e.g., iris. We studied the idea to apply fast eye movements called saccades to verify an authenticated user from among other subjects. We recorded eye movement signals with eye movement cameras using a suitable visual stimulation for a subject. By means of machine learning methods, we classified a subject’s eye movements to verify whether one was an authenticated user. We employed multilayer perceptron networks, radial basis function networks, support vector machines and logistic discriminant analysis for classification. The best accuracy results obtained were approximately 90% and showed that it is possible to verify a subject according to saccade eye movements.

Pages: 85 to 90

Copyright: Copyright (c) IARIA, 2012

Publication date: October 21, 2012

Published in: conference

ISSN: 2326-9332

ISBN: 978-1-61208-227-1

Location: Venice, Italy

Dates: from October 21, 2012 to October 26, 2012