Numerical study on adjusting parameters to improve gaze estimation using planar approximations from electro-oculogram signal voltage ratios
- 4 Downloads
Gaze or eye movements are used as a communication interface in daily life. Herein, we developed a simple method for gaze estimations based on planar approximations of voltage ratios calculated from multiple electro-oculogram signals not affected by drift phenomena, which decrease accuracy. Subsequently, we conducted simulations using an eyeball battery model and investigated the effects of adjusting electrode arrangements, determination coefficients for planar approximations of voltage ratios, and threshold values for angles between simultaneous linear equations, to improve the estimation accuracy and decreased the number of required electrodes. Numerical experiments were used to identify arrangements of six electrodes with errors that were approximately 5° less than those of nine-electrode L-shaped arrangements, indicating improved estimation accuracy with fewer electrodes.
KeywordsGaze estimation Electro-oculography Planar approximation Voltage ratio Numerical experiment
We would like to thank Editage (www.editage.jp) for English language editing.
This study was supported by JSPS Grant-in Aid for Scientific Research 16K00364.
Compliance with ethical standards
Conflict of interest
We have no conflicts of interest or relationship with any companies or commercial organizations.
This study was approved by the research ethics committee of the National Institute of Technology, Toyama College (No. 2).
Human and animal rights
This article does not contain any studies with human participants performed by any of the authors.
- 2.Gips J, Dimattia P, Curran FX, Olivieri P. Using EagleEyes—an electrodes based device for con-trolling the computer with your eyes—to help people with special needs. In: Proc 5th Int Conf Comput helping people with special needs. I; 1996. p. 77–83.Google Scholar
- 3.Tomita Y, Igarashi Y, Honda S, Matsuo N. Electro-oculography mouse for amyotrophic lateral sclerosis patients. Proc IEEE EMBS. 1996;5:1780–1.Google Scholar
- 4.Yagi Y, Koga K, Miyanaga A, Numata H, Funase A, Mukai T. R&D of eye-gaze interface: from basic research to commercialization. In: 44th Annual Conf Jpn Soc Med Biol Eng. OS21-6; 2005. p. 208.Google Scholar
- 5.Yagi T. Eye-gaze interfaces using electro-oculography (EOG). In: Proc 2010 workshop on eye gaze in intelligent human machine interaction; 2010. p. 28–32.Google Scholar
- 6.Tsai JZ, Lee CK, Wu CM, Wu JJ, Kao KP. A feasibility study of an eye-writing system based on electro-oculography. J Med Biol Eng. 2008;28(1):39–46.Google Scholar
- 8.Yan M, Tamura H, Tanno K. A study on gaze estimation system using cross-channels electrooculogram signals. Int Multiconf Eng Comput Sci. 2014;1:112–6.Google Scholar
- 9.Kumar D, Poole E. Classification of EOG for human computer interface. In: Proc Sec Jt EMBS-BMES Conf; 2002. p. 64–67.Google Scholar
- 10.Miyashita H, Hayashi M, Okada K. Implementation of EOG-based gaze estimation in HMD with head-tracker. In: Proc 18th Int Conf Artif Real and Telexistence; 2008. p. 20–27.Google Scholar
- 16.Fujimura Y, Ishida F. Development of gaze estimation method based on voltage-ratio calculated from multi EOG signals. BME Symp. 2012;2012:233–7.Google Scholar
- 17.Itsuki N, Kubo M, Shiraishi S, Nishikawa Y, Mimura Y. A battery model of the eyeball to calculate standing potential of the eye. J Jpn Ophthalmol. Soc. 1995;99:1012–6 (in Japanese).Google Scholar