Classification of EOG for human computer interface

Kumar, D and Poole, E 2002, 'Classification of EOG for human computer interface', in Advanced Concepts For Intelligent Vision Systems, Texas, .


Document type: Conference Paper
Collection: Conference Papers

Title Classification of EOG for human computer interface
Author(s) Kumar, D
Poole, E
Year 2002
Conference name Advanced Concepts For Intelligent Vision Systems
Conference location Texas
Proceedings title Advanced Concepts For Intelligent Vision Systems
Publisher IEEE
Place of publication Texas
Abstract This paper reports the efforts to determine the reliability and limitations of the use of the electro-ocular gram (EOG) for determining the angle of eye gaze for controlling a computer. Consideration has given to determine a general mathematical expression that is subject independent and could be applied to cover all test subjects and generate the required spatial control signals. The EOG signals of five test subjects were recorded while the subjects moved their eyes to view, and then fixate on, specific target points. The target points were effectively located on the shell of a sphere of known radius. Each target point was at a known vertical angle, and known transverse angle from the orthogonal planes that dissect the test subjects eyes in the horizontal plane and the test subjects nose in the vertical plane. The experiments were repeated for determining the EOG relationship for vertical eye movement. The results obtained are encouraging. The assessment of the data suggests that EOG can be successfully utilised for spatial control applications within some limitations. The study recommends the choice of bandwidth for the recording, inter and intra subject reliability, limitation to the angle of the gaze and difference between the vertical and horizontal movement control.
Subjects Biomedical Engineering not elsewhere classified
DOI - identifier 10.1109/IEMBS.2002.1134390
Copyright notice © 2002 IEEE
Versions
Version Filter Type
Altmetric details:
Access Statistics: 345 Abstract Views  -  Detailed Statistics
Created: Tue, 01 Sep 2009, 08:28:58 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us