Lancaster EPrints

Robust Recognition of Reading Activity in Transit Using Wearable Electrooculography

Bulling, Andreas and Ward, Jamie A and Gellersen, Hans and Tröster, Gerhard (2008) Robust Recognition of Reading Activity in Transit Using Wearable Electrooculography. In: Lecture Notes in Computer Science. Springer, pp. 19-37. ISBN 978-3-540-79575-9

[img]
Preview
PDF - Submitted Version
Download (1818Kb) | Preview

    Abstract

    In this work we analyse the eye movements of people in transit in an everyday environment using a wearable electrooculographic (EOG) system. We compare three approaches for continuous recognition of reading activities: a string matching algorithm which exploits typical characteristics of reading signals, such as saccades and fixations; and two variants of Hidden Markov Models (HMMs) - mixed Gaussian and discrete. The recognition algorithms are evaluated in an experiment performed with eight subjects reading freely chosen text without pictures while sitting at a desk, standing, walking indoors and outdoors, and riding a tram. A total dataset of roughly 6 hours was collected with reading activity accounting for about half of the time. We were able to detect reading activities over all subjects with a top recognition rate of 80.2% (71.0% recall, 11.6% false positives) using string matching. We show that EOG is a potentially robust technique for reading recognition across a number of typical daily situations.

    Item Type: Contribution in Book/Report/Proceedings
    Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
    Departments: Faculty of Science and Technology > School of Computing & Communications
    ID Code: 13046
    Deposited By: ep_importer_comp
    Deposited On: 25 Jun 2008 19:59
    Refereed?: No
    Published?: Published
    Last Modified: 23 Oct 2017 02:33
    Identification Number:
    URI: http://eprints.lancs.ac.uk/id/eprint/13046

    Actions (login required)

    View Item