Towards complete and accurate iris segmentation using deep multi-task attention network for non-cooperative iris recognition

C Wang, J Muhammad, Y Wang, Z He… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
Iris images captured in non-cooperative environments often suffer from adverse noise, which
challenges many existing iris segmentation methods. To address this problem, this paper …

Learning to find eye region landmarks for remote gaze estimation in unconstrained settings

S Park, X Zhang, A Bulling, O Hilliges - … of the 2018 ACM symposium on …, 2018 - dl.acm.org
Conventional feature-based and model-based gaze estimation methods have proven to
perform well in settings with controlled illumination and specialized cameras. In …

Teyed: Over 20 million real-world eye images with pupil, eyelid, and iris 2d and 3d segmentations, 2d and 3d landmarks, 3d eyeball, gaze vector, and eye movement …

W Fuhl, G Kasneci, E Kasneci - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
We present TEyeD, the world's largest unified public data set of eye images taken with head-
mounted devices. TEyeD was acquired with seven different head-mounted eye trackers …

PuRe: Robust pupil detection for real-time pervasive eye tracking

T Santini, W Fuhl, E Kasneci - Computer Vision and Image Understanding, 2018 - Elsevier
Real-time, accurate, and robust pupil detection is an essential prerequisite to enable
pervasive eye-tracking and its applications–eg, gaze-based human computer interaction …

Eye‐Tracking as a Tool to Evaluate Functional Ability in Everyday Tasks in Glaucoma

E Kasneci, AA Black, JM Wood - Journal of ophthalmology, 2017 - Wiley Online Library
To date, few studies have investigated the eye movement patterns of individuals with
glaucoma while they undertake everyday tasks in real‐world settings. While some of these …

1000 pupil segmentations in a second using haar like features and statistical learning

W Fuhl, J Schneider, E Kasneci - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
In this paper we present a new approach for pupil segmentation. It can be computed and
trained very efficiently, making it ideal for online use for high speed eye trackers as well as …

The gaze and mouse signal as additional source for user fingerprints in browser applications

W Fuhl, D Weber, S Eivazi - arxiv preprint arxiv:2101.03793, 2021 - arxiv.org
In this work, we inspect different data sources for browser fingerprints. We show which
disadvantages and limitations browser statistics have and how this can be avoided with …

A multimodal eye movement dataset and a multimodal eye movement segmentation analysis

W Fuhl, E Kasneci - ACM Symposium on Eye Tracking Research and …, 2021 - dl.acm.org
We present a new dataset with annotated eye movements. The dataset consists of over
800,000 gaze points recorded during a car ride in the real world and in the simulator. In total …

Groupgazer: A tool to compute the gaze per participant in groups with integrated calibration to map the gaze online to a screen or beamer projection

W Fuhl, D Weber, S Eivazi - arxiv preprint arxiv:2201.07692, 2022 - arxiv.org
In this paper we present GroupGaze. It is a tool that can be used to calculate the gaze
direction and the gaze position of whole groups. GroupGazer calculates the gaze direction …

Tensor normalization and full distribution training

W Fuhl - arxiv preprint arxiv:2109.02345, 2021 - arxiv.org
In this work, we introduce pixel wise tensor normalization, which is inserted after rectifier
linear units and, together with batch normalization, provides a significant improvement in the …