Abstract

The technology for determining eye gaze direction on a monitor screen is considered by analyzing the images received from a video camera directed at a user without using additional equipment. We propose a combined convolutional neural network extracting high-level features of images with a neural network of long short-term memory that takes into account the temporal dynamics of oculomotor activity. To train the model, a representative database of video sequences with reference information concerning eye direction was collected. Experiments confirmed that accounting for temporal information increased the accuracy of recording the eye direction.

© 2018 Optical Society of America

Use of artificial neural networks on optical track width measurements

Richard J. Smith, Chung W. See, Mike G. Somekh, and Andrew Yacoot
Appl. Opt. 46(22) 4857-4866 (2007)

Signal processing using artificial neural network for BOTDA sensor system

Abul Kalam Azad, Liang Wang, Nan Guo, Hwa-Yaw Tam, and Chao Lu
Opt. Express 24(6) 6769-6782 (2016)

Processing wave-front-sensor slope measurements using artificial neural networks

Dennis A. Montera, Byron M. Welsh, Michael C. Roggemann, and Dennis W. Ruck
Appl. Opt. 35(21) 4238-4251 (1996)

Artificial neural superposition eye

Andreas Brückner, Jacques Duparré, Peter Dannberg, Andreas Bräuer, and Andreas Tünnermann
Opt. Express 15(19) 11922-11933 (2007)

Eye-tracking architecture for biometrics and remote monitoring

Ashit Talukder, John-Michael Morookian, Steve Monacos, Raymond Lam, Clayton LeBaw, and James L. Lambert
Appl. Opt. 44(5) 693-700 (2005)