pith. sign in

arxiv: 1907.04325 · v1 · pith:WF6BZROXnew · submitted 2019-07-09 · 💻 cs.CV

Image based Eye Gaze Tracking and its Applications

Anjith George This is my paper

Pith reviewed 2026-05-25 00:18 UTC · model grok-4.3

classification 💻 cs.CV
keywords eye trackingiris localizationgaze estimationconvolutional neural networksbiometricsactivity recognitionhuman computer interaction
0
0 comments X

The pith

Image-based algorithms track eye gaze without user calibration or special hardware.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents methods to estimate eye gaze from ordinary images to make human-computer interaction more natural and affordable. It introduces a two-stage process to locate the iris center even when images are blurred by motion, contain reflections, or have uneven lighting. A convolutional neural network then classifies the direction of gaze without needing any person-specific training data. These tools are used to create systems for identifying people from their eye movements and for recognizing daily activities by merging gaze information with head motion and scene features.

Core claim

The work establishes a two-stage iris center localization algorithm that operates under motion blur, glint, and varying illumination, along with a person-independent convolutional neural network framework for gaze direction classification that requires no user-specific calibration. These enable biometric identification from eye movement parameters and activity recognition by integrating gaze data, ego-motion, and visual features from head-mounted trackers.

What carries the argument

The two-stage iris center localization algorithm and the person-independent CNN gaze classifier.

Load-bearing premise

The new iris localization and CNN-based classification will maintain high performance in real-world scenarios without requiring any user calibration or specialized equipment.

What would settle it

A test on video sequences containing motion blur, specular reflections, and illumination changes where the iris center localization error and gaze classification accuracy are measured without per-user training data.

Figures

Figures reproduced from arXiv: 1907.04325 by Anjith George.

Figure 1.1
Figure 1.1. Figure 1.1: External anatomy of eye, a) Frontal view, b)Side view. [PITH_FULL_IMAGE:figures/full_fig_p035_1_1.png] view at source ↗
Figure 1.2
Figure 1.2. Figure 1.2: Eye image captured under, a) Visible light, b) NIR lighting. [PITH_FULL_IMAGE:figures/full_fig_p036_1_2.png] view at source ↗
Figure 1.3
Figure 1.3. Figure 1.3: Different types of eye trackers, a) Remote eye tracker, b) Head [PITH_FULL_IMAGE:figures/full_fig_p039_1_3.png] view at source ↗
Figure 2.1
Figure 2.1. Figure 2.1: Stages in ellipse fitting: (a) Cropped eye region, (b) Correlation surface [PITH_FULL_IMAGE:figures/full_fig_p054_2_1.png] view at source ↗
Figure 2.2
Figure 2.2. Figure 2.2: Transformation of estimated gaze point to screen coordinates for com [PITH_FULL_IMAGE:figures/full_fig_p061_2_2.png] view at source ↗
Figure 2.3
Figure 2.3. Figure 2.3: Few samples showing successful detections (first row) and failures [PITH_FULL_IMAGE:figures/full_fig_p063_2_3.png] view at source ↗
Figure 2.4
Figure 2.4. Figure 2.4: Performance of the proposed algorithm in BioID and Gi4E databases. [PITH_FULL_IMAGE:figures/full_fig_p064_2_4.png] view at source ↗
Figure 2.5
Figure 2.5. Figure 2.5: Some samples showing successful detections (first row) and failures [PITH_FULL_IMAGE:figures/full_fig_p064_2_5.png] view at source ↗
Figure 2.6
Figure 2.6. Figure 2.6: WEC Performance of the proposed algorithm in (a) BioID and (b) [PITH_FULL_IMAGE:figures/full_fig_p065_2_6.png] view at source ↗
Figure 2.7
Figure 2.7. Figure 2.7: WEC performance comparison of proposed method with state of the [PITH_FULL_IMAGE:figures/full_fig_p066_2_7.png] view at source ↗
Figure 2.8
Figure 2.8. Figure 2.8: WEC performance comparison of the proposed method with gradient [PITH_FULL_IMAGE:figures/full_fig_p067_2_8.png] view at source ↗
Figure 2.9
Figure 2.9. Figure 2.9: Sample images of subjects in the experiment. [PITH_FULL_IMAGE:figures/full_fig_p070_2_9.png] view at source ↗
Figure 2.10
Figure 2.10. Figure 2.10: Sample images of detections in the custom dataset [PITH_FULL_IMAGE:figures/full_fig_p070_2_10.png] view at source ↗
Figure 2.11
Figure 2.11. Figure 2.11: PoG estimates with 16 and 9 point calibration grids (a),(c) poly [PITH_FULL_IMAGE:figures/full_fig_p071_2_11.png] view at source ↗
Figure 3.1
Figure 3.1. Figure 3.1: Sample images from the LPW dataset frared) images. • The proposed approach combines multiple sources of information like inten￾sity and edges for finding the pupil center • A multistage filtering of candidates is proposed which reduces the error in the final estimate using a scale space approach • A simple yet effective pupil tracking scheme is also included for enhanced detection rates and speed. 3.2 Re… view at source ↗
Figure 3.2
Figure 3.2. Figure 3.2: Flowchart of the proposed approach After obtaining the normalized image, Canny edge detection algorithm is em￾ployed for detecting the edges. However, directly applying Canny algorithm over the eye image results in a lot of spurious edges. In our case, the task is to iden￾tify the pupil boundary. Since the region inside pupil is somewhat homogeneous, detection of false edges can be reduced by convolving … view at source ↗
Figure 3.3
Figure 3.3. Figure 3.3: Edge based ellipse fitting, a) The original color image captured, b) [PITH_FULL_IMAGE:figures/full_fig_p083_3_3.png] view at source ↗
Figure 3.4
Figure 3.4. Figure 3.4: Intensity based ellipse fitting, a) The original color image captured, b) [PITH_FULL_IMAGE:figures/full_fig_p084_3_4.png] view at source ↗
Figure 3.5
Figure 3.5. Figure 3.5: The proposed approach outperforms all the state of the art methods. [PITH_FULL_IMAGE:figures/full_fig_p086_3_5.png] view at source ↗
Figure 3.5
Figure 3.5. Figure 3.5: Detection rates of the algorithms in LPW dataset ( ElSe, ExCuSe, [PITH_FULL_IMAGE:figures/full_fig_p088_3_5.png] view at source ↗
Figure 3.7
Figure 3.7. Figure 3.7: Sample results from the detections, the first row shows the successful [PITH_FULL_IMAGE:figures/full_fig_p088_3_7.png] view at source ↗
Figure 3.6
Figure 3.6. Figure 3.6: Detection rates with and without tracking. [PITH_FULL_IMAGE:figures/full_fig_p089_3_6.png] view at source ↗
Figure 3.8
Figure 3.8. Figure 3.8: Some examples of the challenging images from datasets 4 and 5 [PITH_FULL_IMAGE:figures/full_fig_p089_3_8.png] view at source ↗
Figure 4.1
Figure 4.1. Figure 4.1: Different EACs in NLP theory 4.1.1 Application in finding Eye Accessing Cues The patterns in which the eyes move when humans access their memories is known as eye accessing cues (EAC). The neuro-linguistic programming (NLP) EAC the￾ory suggests [94] that there is a correlation between eye-movements and cognitive processing while accessing experiences. EAC theory suggests that the meaning of non-visual ga… view at source ↗
Figure 4.2
Figure 4.2. Figure 4.2: Schematic of the overall framework 4.3.1 Face detection and eye region localization The first stage in the algorithm is face detection. The framework described in Chapter 2 is used for face detection. Once the face region is localized, next stage 64 [PITH_FULL_IMAGE:figures/full_fig_p096_4_2.png] view at source ↗
Figure 4.3
Figure 4.3. Figure 4.3: Eye region localization using geometric approach (ROI) [PITH_FULL_IMAGE:figures/full_fig_p097_4_3.png] view at source ↗
Figure 4.4
Figure 4.4. Figure 4.4: Eye region localization using ERT approach [PITH_FULL_IMAGE:figures/full_fig_p097_4_4.png] view at source ↗
Figure 4.5
Figure 4.5. Figure 4.5: Architecture of the CNN used 4.3.2.2 Classification of eye gaze direction Two CNNs are trained independently for left and right eyes. The scores from both the networks are used to obtain the average score. score =  scoreL + scoreR 2  (4.3) where, scoreL and scoreR denote the scores obtained from left and right CNNs respectively. The class can be found out as the label with maximum probability: class = … view at source ↗
Figure 4.6
Figure 4.6. Figure 4.6: Sample results from the framework 4.4.2 Results The results obtained from the experiments in Eye Chimera dataset is described in this section. The classification accuracy was high in 3-class scenario compared to 69 [PITH_FULL_IMAGE:figures/full_fig_p101_4_6.png] view at source ↗
Figure 4
Figure 4. Figure 4: and Fig. 4.8 [PITH_FULL_IMAGE:figures/full_fig_p102_4.png] view at source ↗
Figure 4.7
Figure 4.7. Figure 4.7: Confusion matrix for 3 classes (ERT+CNN) [PITH_FULL_IMAGE:figures/full_fig_p104_4_7.png] view at source ↗
Figure 4.8
Figure 4.8. Figure 4.8: Confusion matrix for 7 classes (ERT+CNN) [PITH_FULL_IMAGE:figures/full_fig_p104_4_8.png] view at source ↗
Figure 5.1
Figure 5.1. Figure 5.1: The arrangement for gaze recording Raw eye gaze positions may contain noise. Most of the features used in this work are extracted from velocity and acceleration profiles. The presence of noise makes it difficult to estimate the velocity and acceleration parameters using dif￾ferentiation operation. Eye movement signals contain high-frequency components, especially during saccades. High-frequency component… view at source ↗
Figure 5.2
Figure 5.2. Figure 5.2: Gaze data and stimulus for RAN 30min sequence A minimum duration threshold of 100 ms has been chosen to reduce the false positives in fixation identification. Algorithm 2 returns the classification results for each data point as either fixation or saccade. Points that are not a part of fixations are considered as saccades in this stage. In the proposed approach, we consider saccades with their durations … view at source ↗
Figure 5.3
Figure 5.3. Figure 5.3: Classification of the raw sequence [PITH_FULL_IMAGE:figures/full_fig_p116_5_3.png] view at source ↗
Figure 5.4
Figure 5.4. Figure 5.4: Schematic of the proposed framework. 91 [PITH_FULL_IMAGE:figures/full_fig_p123_5_4.png] view at source ↗
Figure 5.5
Figure 5.5. Figure 5.5: CMC curve for (a) RAN 30min and (b) TEX 30min [PITH_FULL_IMAGE:figures/full_fig_p128_5_5.png] view at source ↗
Figure 5.6
Figure 5.6. Figure 5.6: CMC curve for (a) RAN 1year and (b) TEX 1year The detection error trade-off (DET) curves for the development datasets are shown in [PITH_FULL_IMAGE:figures/full_fig_p128_5_6.png] view at source ↗
Figure 5.7
Figure 5.7. Figure 5.7: DET curve for (a) RAN 30min and (b) TEX 30min 97 [PITH_FULL_IMAGE:figures/full_fig_p129_5_7.png] view at source ↗
Figure 5.8
Figure 5.8. Figure 5.8: DET curve for (a) RAN 1year and (b) TEX 1year 5.4.3.2 Performance in the evaluation sets The evaluation part of the database is unlabeled. However, the results of the competition are available on the website [132]. The evaluation set of the dataset had only one unlabeled data for every labeled sample. We have used this one to one correspondence assumption in the final stage of the algorithm. Let there be… view at source ↗
Figure 6.1
Figure 6.1. Figure 6.1: The activity classes considered in the work, a) Read, b) Watching [PITH_FULL_IMAGE:figures/full_fig_p136_6_1.png] view at source ↗
Figure 6.2
Figure 6.2. Figure 6.2: The proposed framework, three channels of information are fused to [PITH_FULL_IMAGE:figures/full_fig_p139_6_2.png] view at source ↗
Figure 6.3
Figure 6.3. Figure 6.3: CNN feature extraction scheme, cropped and resized image is fed into [PITH_FULL_IMAGE:figures/full_fig_p140_6_3.png] view at source ↗
Figure 6.4
Figure 6.4. Figure 6.4: The normalized histogram of the string sequence over a sliding temporal win￾dow is used as the feature for classification. 109 [PITH_FULL_IMAGE:figures/full_fig_p141_6_4.png] view at source ↗
Figure 6.4
Figure 6.4. Figure 6.4: Motion encoding scheme. 6.3.3 Feature extraction from motion Motion features are extracted from the optical flow between subsequent frames. Let the i th frame be denoted as Fi . For each frame, corner detection is performed to obtain the candidate points to track. The points are tracked using Lucas-Kanade optical flow. Successfully tracked points are found out using forward-backward error [164]. The medi… view at source ↗
Figure 6.5
Figure 6.5. Figure 6.5: Normalized confusion matrix for five classes, a) Combined features, b) [PITH_FULL_IMAGE:figures/full_fig_p145_6_5.png] view at source ↗
Figure 6.6
Figure 6.6. Figure 6.6: Normalized confusion matrix for six classes, a) Combined features, b) [PITH_FULL_IMAGE:figures/full_fig_p146_6_6.png] view at source ↗
Figure 6.7
Figure 6.7. Figure 6.7: Variation of accuracy across different subjects [PITH_FULL_IMAGE:figures/full_fig_p146_6_7.png] view at source ↗
Figure 6.8
Figure 6.8. Figure 6.8: The joint representation achieves better results as compared to the [PITH_FULL_IMAGE:figures/full_fig_p147_6_8.png] view at source ↗
Figure 6.9
Figure 6.9. Figure 6.9: Comparison with state of the art methods [1], SW+MW (Saccade [PITH_FULL_IMAGE:figures/full_fig_p148_6_9.png] view at source ↗
read the original abstract

Eye movements play a vital role in perceiving the world. Eye gaze can give a direct indication of the users point of attention, which can be useful in improving human-computer interaction. Gaze estimation in a non-intrusive manner can make human-computer interaction more natural. Eye tracking can be used for several applications such as fatigue detection, biometric authentication, disease diagnosis, activity recognition, alertness level estimation, gaze-contingent display, human-computer interaction, etc. Even though eye-tracking technology has been around for many decades, it has not found much use in consumer applications. The main reasons are the high cost of eye tracking hardware and lack of consumer level applications. In this work, we attempt to address these two issues. In the first part of this work, image-based algorithms are developed for gaze tracking which includes a new two-stage iris center localization algorithm. We have developed a new algorithm which works in challenging conditions such as motion blur, glint, and varying illumination levels. A person independent gaze direction classification framework using a convolutional neural network is also developed which eliminates the requirement of user-specific calibration. In the second part of this work, we have developed two applications which can benefit from eye tracking data. A new framework for biometric identification based on eye movement parameters is developed. A framework for activity recognition, using gaze data from a head-mounted eye tracker is also developed. The information from gaze data, ego-motion, and visual features are integrated to classify the activities.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The manuscript claims to develop image-based eye gaze tracking algorithms, including a new two-stage iris center localization method robust to motion blur, glint, and varying illumination, plus a person-independent CNN framework for gaze direction classification that removes the need for user-specific calibration. It further presents two applications: a biometric identification system based on eye movement parameters and an activity recognition framework that integrates gaze data from a head-mounted tracker with ego-motion and visual features.

Significance. If the robustness and calibration-free claims hold with strong validation, the work would be significant for advancing accessible, non-intrusive eye tracking in consumer HCI, biometrics, and activity recognition by lowering hardware and setup barriers. The dual focus on core algorithms and integrated applications is a strength, though the absence of reported metrics makes the practical impact difficult to evaluate.

major comments (1)
  1. [Abstract] Abstract: The central claims of a two-stage iris localization algorithm that 'works in challenging conditions' and a CNN framework that 'eliminates the requirement of user-specific calibration' are presented without any quantitative results, error rates, datasets, or validation details. This directly undermines assessment of the load-bearing assertions about real-world reliability and person-independence.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their review and the opportunity to respond. We address the major comment on the abstract below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The central claims of a two-stage iris localization algorithm that 'works in challenging conditions' and a CNN framework that 'eliminates the requirement of user-specific calibration' are presented without any quantitative results, error rates, datasets, or validation details. This directly undermines assessment of the load-bearing assertions about real-world reliability and person-independence.

    Authors: We agree that the abstract would be strengthened by including quantitative results to support the central claims. The full manuscript reports experimental validation of the two-stage iris center localization (including performance under motion blur, glint, and illumination variation) and the person-independent CNN gaze classifier on appropriate datasets with error rates and accuracy metrics. In the revised version we will update the abstract to incorporate key quantitative details such as error rates, datasets used, and validation outcomes. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper presents algorithmic developments for iris localization and CNN-based gaze classification without any equations, derivations, fitted parameters relabeled as predictions, or load-bearing self-citations. Claims rest on new method descriptions and testing under listed conditions rather than any chain that reduces to its own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract contains no mathematical derivations, fitted parameters, axioms, or new postulated entities; work is described at the level of algorithmic development in computer vision.

pith-pipeline@v0.9.0 · 5784 in / 964 out tokens · 26065 ms · 2026-05-25T00:18:30.784422+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

180 extracted references · 180 canonical work pages · 5 internal anchors

  1. [1]

    Coupling eye-motion and ego-motion features for first-person activity recognition,

    K. Ogaki, K. M. Kitani, Y. Sugano, and Y. Sato, “Coupling eye-motion and ego-motion features for first-person activity recognition,” in Conference on Computer Vision and Pat- tern Recognition Workshops. IEEE, 2012, pp. 1–7

    work page 2012

  2. [2]

    Fast unsupervised ego-action learn- ing for first-person sports videos,

    K. M. Kitani, T. Okabe, Y. Sato, and A. Sugimoto, “Fast unsupervised ego-action learn- ing for first-person sports videos,” in Computer Vision and Pattern Recognition, IEEE Conference on, 2011, pp. 3241–3248

    work page 2011

  3. [3]

    Modeling the shape of the scene: A holistic representation of the spatial envelope,

    A. Oliva and A. Torralba, “Modeling the shape of the scene: A holistic representation of the spatial envelope,” International journal of computer vision , vol. 42, no. 3, pp. 145–175, 2001

    work page 2001

  4. [4]

    Design and Implementation of Real-time Algorithms for Eye Tracking and PERCLOS Measurement for on board Estimation of Alertness of Drivers

    A. George and A. Routray, “Design and implementation of real-time algorithms for eye tracking and perclos measurement for on board estimation of alertness of drivers,” arXiv preprint arXiv:1505.06162, 2015

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  5. [5]

    Duchowski, Eye tracking methodology: Theory and practice

    A. Duchowski, Eye tracking methodology: Theory and practice . Springer Science & Busi- ness Media, 2007, vol. 373

    work page 2007

  6. [6]

    A video database of human faces under near infra-red illumination for human computer interaction applications,

    S. Happy, A. Dasgupta, A. George, and A. Routray, “A video database of human faces under near infra-red illumination for human computer interaction applications,” in 2012 4th International Conference on Intelligent Human Computer Interaction (IHCI) . IEEE, 2012, pp. 1–4

    work page 2012

  7. [7]

    Survey of eye movement recording methods,

    L. R. Young and D. Sheena, “Survey of eye movement recording methods,” Behavior research methods & instrumentation, vol. 7, no. 5, pp. 397–429, 1975

    work page 1975

  8. [8]

    Mechanism of saccadic eye movements,

    G. Westheimer, “Mechanism of saccadic eye movements,” AMA Archives of Ophthalmol- ogy, vol. 52, no. 5, pp. 710–724, 1954

    work page 1954

  9. [9]

    Eye gaze tracking techniques for interactive applica- tions,

    C. H. Morimoto and M. R. Mimica, “Eye gaze tracking techniques for interactive applica- tions,” Computer Vision and Image Understanding , vol. 98, no. 1, pp. 4–24, 2005

    work page 2005

  10. [10]

    Real-time eye detection and tracking for driver observa- tion under various light conditions,

    X. Liu, F. Xu, and K. Fujimura, “Real-time eye detection and tracking for driver observa- tion under various light conditions,” in Intelligent Vehicle Symposium, IEEE , vol. 2, 2002, pp. 344–351

    work page 2002

  11. [11]

    A real-time eye detection system based on the active ir illumination,

    Z. Guang-yuan, C. Bo, J. Zhe, and L. Jia-wen, “A real-time eye detection system based on the active ir illumination,” in Chinese Control and Decision Conference. IEEE, 2008, pp. 1255–1260

    work page 2008

  12. [12]

    Low cost eye tracking: The current panorama,

    O. Ferhat and F. Vilari˜ no, “Low cost eye tracking: The current panorama,”Computational intelligence and neuroscience, 2016

    work page 2016

  13. [13]

    A mul- timodal system for assessing alertness levels due to cognitive loading,

    A. Sengupta, A. Dasgupta, A. Chaudhuri, A. George, A. Routray, and R. Guha, “A mul- timodal system for assessing alertness levels due to cognitive loading,” IEEE Transactions on Neural Systems and Rehabilitation Engineering , vol. 25, no. 7, pp. 1037–1046, 2017

    work page 2017

  14. [14]

    Alertness monitoring system for vehicle drivers using physiological signals,

    A. Sengupta, A. George, A. Dasgupta, A. Chaudhuri, B. Kabi, and A. Routray, “Alertness monitoring system for vehicle drivers using physiological signals,” in Handbook of Research on Emerging Innovations in Rail Transportation Engineering. IGI Global, 2016, pp. 273– 311. 129

    work page 2016

  15. [15]

    An Improved Algorithm for Eye Corner Detection

    A. Dasgupta, B. Kabi, A. George, S. Happy, and A. Routray, “A drowsiness detection scheme based on fusion of voice and vision cues,” arXiv preprint arXiv:1509.04887 , 2015

    work page internal anchor Pith review Pith/arXiv arXiv 2015

  16. [16]

    Eye movements in biometrics,

    P. Kasprowski and J. Ober, “Eye movements in biometrics,” in International Workshop on Biometric Authentication. Springer, 2004, pp. 248–258

    work page 2004

  17. [17]

    Gazesim: simulating foveated rendering using depth in eye gaze for vr,

    Y. S. Pai, B. Tag, B. Outram, N. Vontin, K. Sugiura, and K. Kunze, “Gazesim: simulating foveated rendering using depth in eye gaze for vr,” in ACM SIGGRAPH Posters , 2016, p. 75

    work page 2016

  18. [18]

    Gaze-contingent displays: A review,

    A. T. Duchowski, N. Cournia, and H. Murphy, “Gaze-contingent displays: A review,” CyberPsychology & Behavior, vol. 7, no. 6, pp. 621–634, 2004

    work page 2004

  19. [19]

    A breadth-first survey of eye-tracking applications,

    A. T. Duchowski, “A breadth-first survey of eye-tracking applications,” Behavior Research Methods, Instruments, & Computers , vol. 34, no. 4, pp. 455–470, 2002

    work page 2002

  20. [20]

    Eye tracking in human-computer interaction and usability research: Ready to deliver the promises,

    R. Jacob and K. S. Karn, “Eye tracking in human-computer interaction and usability research: Ready to deliver the promises,” Mind, vol. 2, no. 3, p. 4, 2003

    work page 2003

  21. [21]

    Manual and gaze input cascaded (magic) pointing,

    S. Zhai, C. Morimoto, and S. Ihde, “Manual and gaze input cascaded (magic) pointing,” pp. 246–253, 1999

    work page 1999

  22. [22]

    Perceptually-based foveated virtual reality,

    A. Patney, J. Kim, M. Salvi, A. Kaplanyan, C. Wyman, N. Benty, A. Lefohn, and D. Lue- bke, “Perceptually-based foveated virtual reality,” in ACM SIGGRAPH Emerging Tech- nologies, 2016, p. 17

    work page 2016

  23. [23]

    Eye tracking and eye-based human–computer interaction,

    P. Majaranta and A. Bulling, “Eye tracking and eye-based human–computer interaction,” in Advances in physiological computing. Springer, 2014, pp. 39–65

    work page 2014

  24. [24]

    Twenty years of eye typing: systems and design issues,

    P. Majaranta and K.-J. R¨ aih¨ a, “Twenty years of eye typing: systems and design issues,” in Symposium on Eye tracking research & applications . ACM, 2002, pp. 15–22

    work page 2002

  25. [25]

    Dynamics of saccadic eye move- ment depending on diurnal variation in human alertness,

    A. Ueno, T. Tateyama, M. Takase, and H. Minamitani, “Dynamics of saccadic eye move- ment depending on diurnal variation in human alertness,” Systems and Computers in Japan, vol. 33, no. 7, pp. 95–103, 2002

    work page 2002

  26. [26]

    A critical review of past research into the neuro-linguistic programming eye-accessing cues model,

    G. Diamantopoulos, S. I. Woolley, and M. Spann, “A critical review of past research into the neuro-linguistic programming eye-accessing cues model,” Current Research in NLP , p. 8, 2009

    work page 2009

  27. [27]

    R. J. Leigh and D. S. Zee, The neurology of eye movements . Oxford University Press, USA, 2015, vol. 90

    work page 2015

  28. [28]

    Eye tracking dysfunction in schizophrenia: characterization and pathophysiology,

    D. L. Levy, A. B. Sereno, D. C. Gooding, and G. A. ODriscoll, “Eye tracking dysfunction in schizophrenia: characterization and pathophysiology,” in Behavioral Neurobiology of Schizophrenia and Its Treatment. Springer, 2010, pp. 311–347

    work page 2010

  29. [29]

    Majaranta, Gaze Interaction and Applications of Eye Tracking: Advances in Assistive Technologies: Advances in Assistive Technologies

    P. Majaranta, Gaze Interaction and Applications of Eye Tracking: Advances in Assistive Technologies: Advances in Assistive Technologies. IGI Global, 2011

    work page 2011

  30. [30]

    In the eye of the beholder: A survey of models for eyes and gaze,

    D. W. Hansen and Q. Ji, “In the eye of the beholder: A survey of models for eyes and gaze,” Pattern Analysis and Machine Intelligence, IEEE Transactions on , vol. 32, no. 3, pp. 478–500, 2010

    work page 2010

  31. [31]

    Appearance-based gaze estimation in the wild,

    X. Zhang, Y. Sugano, M. Fritz, and A. Bulling, “Appearance-based gaze estimation in the wild,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recogni- tion, 2015, pp. 4511–4520. 130

    work page 2015

  32. [32]

    A survey of the hough transform,

    J. Illingworth and J. Kittler, “A survey of the hough transform,” Computer vision, graph- ics, and image processing , vol. 44, no. 1, pp. 87–116, 1988

    work page 1988

  33. [33]

    Young, H

    D. Young, H. Tunley, and R. Samuels, Specialised hough transform and active contour methods for real-time eye tracking. University of Sussex, Cognitive & Computing Science, 1995

    work page 1995

  34. [34]

    Circular object detection using a modified hough transform,

    M. Smereka and I. Duleba, “Circular object detection using a modified hough transform,” International Journal of Applied Mathematics and Computer Science , vol. 18, no. 1, pp. 85–91, 2008

    work page 2008

  35. [35]

    Size invariant circle detection,

    T. J. Atherton and D. J. Kerbyson, “Size invariant circle detection,” Image and Vision computing, vol. 17, no. 11, pp. 795–803, 1999

    work page 1999

  36. [36]

    A novel pupil localization method based on gabor- eye model and radial symmetry operator,

    P. Yang, B. Du, S. Shan, and W. Gao, “A novel pupil localization method based on gabor- eye model and radial symmetry operator,” in Image Processing, International Conference on, vol. 1. IEEE, 2004, pp. 67–70

    work page 2004

  37. [37]

    Accurate eye center location through invariant isocentric pat- terns,

    R. Valenti and T. Gevers, “Accurate eye center location through invariant isocentric pat- terns,” Pattern Analysis and Machine Intelligence, IEEE Transactions on , vol. 34, no. 9, pp. 1785–1798, 2012

    work page 2012

  38. [38]

    Combining head pose and eye location information for gaze estimation,

    R. Valenti, N. Sebe, and T. Gevers, “Combining head pose and eye location information for gaze estimation,” Image Processing, IEEE Transactions on, vol. 21, no. 2, pp. 802–815, 2012

    work page 2012

  39. [39]

    Accurate eye centre localisation by means of gradients

    F. Timm and E. Barth, “Accurate eye centre localisation by means of gradients.” VISAPP, vol. 11, pp. 125–130, 2011

    work page 2011

  40. [40]

    A ball detection algorithm for real soccer image sequences,

    T. D’Orazio, N. Ancona, G. Cicirelli, and M. Nitti, “A ball detection algorithm for real soccer image sequences,” in Pattern Recognition, 16th International Conference on, vol. 1. IEEE, 2002, pp. 210–213

    work page 2002

  41. [41]

    How iris recognition works,

    J. Daugman, “How iris recognition works,” Circuits and Systems for Video Technology, IEEE Transactions on, vol. 14, no. 1, pp. 21–30, 2004

    work page 2004

  42. [42]

    Eyeball model-based iris center localization for visible image-based eye-gaze tracking systems,

    S.-J. Baek, K.-A. Choi, C. Ma, Y.-H. Kim, and S.-J. Ko, “Eyeball model-based iris center localization for visible image-based eye-gaze tracking systems,” Consumer Electronics, IEEE Transactions on, vol. 59, no. 2, pp. 415–421, 2013

    work page 2013

  43. [43]

    Real-time eye gaze tracking with an unmodified com- modity webcam employing a neural network,

    W. Sewell and O. Komogortsev, “Real-time eye gaze tracking with an unmodified com- modity webcam employing a neural network,” in CHI’10 Extended Abstracts on Human Factors in Computing Systems . ACM, 2010, pp. 3739–3744

    work page 2010

  44. [44]

    Projection functions for eye detection,

    Z.-H. Zhou and X. Geng, “Projection functions for eye detection,” Pattern recognition, vol. 37, no. 5, pp. 1049–1056, 2004

    work page 2004

  45. [45]

    Blink detection and eye track- ing for eye localization,

    T. Bhaskar, F. T. Keat, S. Ranganath, and Y. Venkatesh, “Blink detection and eye track- ing for eye localization,” in Conference on Convergent Technologies for the Asia-Pacific Region, vol. 2. IEEE, 2003, pp. 821–824

    work page 2003

  46. [46]

    Eye gaze estimation from a single image of one eye,

    J. Wang, E. Sung, and R. Venkateswarlu, “Eye gaze estimation from a single image of one eye,” in Computer Vision, Ninth IEEE International Conference on , 2003, pp. 136–143

    work page 2003

  47. [47]

    Eye pupil local- ization with an ensemble of randomized trees,

    N. Markuˇ s, M. Frljak, I. S. Pandˇ zi´ c, J. Ahlberg, and R. Forchheimer, “Eye pupil local- ization with an ensemble of randomized trees,” Pattern recognition, vol. 47, no. 2, pp. 578–587, 2014. 131

    work page 2014

  48. [48]

    Manifold alignment for person inde- pendent appearance-based gaze estimation,

    T. Schneider, B. Schauerte, and R. Stiefelhagen, “Manifold alignment for person inde- pendent appearance-based gaze estimation,” in 22nd International Conference on Pattern Recognition. IEEE, 2014, pp. 1167–1172

    work page 2014

  49. [49]

    Learning-by-synthesis for appearance-based 3d gaze estimation,

    Y. Sugano, Y. Matsushita, and Y. Sato, “Learning-by-synthesis for appearance-based 3d gaze estimation,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 1821–1828

    work page 2014

  50. [50]

    Rapid object detection using a boosted cascade of simple features,

    P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” in Computer Vision and Pattern Recognition. Proceedings of the IEEE Computer Society Conference on, vol. 1, 2001, pp. I–511

    work page 2001

  51. [51]

    A vision-based system for monitoring the loss of attention in automotive drivers,

    A. Dasgupta, A. George, S. Happy, and A. Routray, “A vision-based system for monitoring the loss of attention in automotive drivers,” IEEE Transactions on Intelligent Transporta- tion Systems, vol. 14, no. 4, pp. 1825–1838, 2013

    work page 2013

  52. [52]

    Starburst: A hybrid algorithm for video-based eye tracking combining feature-based and model-based approaches,

    D. Li, D. Winfield, and D. J. Parkhurst, “Starburst: A hybrid algorithm for video-based eye tracking combining feature-based and model-based approaches,” in Computer Vision and Pattern Recognition-Workshops, IEEE Computer Society Conference on , 2005, pp. 79–79

    work page 2005

  53. [53]

    Direct least square fitting of ellipses,

    A. Fitzgibbon, M. Pilu, and R. B. Fisher, “Direct least square fitting of ellipses,” Pattern Analysis and Machine Intelligence, IEEE Transactions on , vol. 21, no. 5, pp. 476–480, 1999

    work page 1999

  54. [54]

    Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,

    M. A. Fischler and R. C. Bolles, “Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography,” Communications of the ACM, vol. 24, no. 6, pp. 381–395, 1981

    work page 1981

  55. [55]

    Robust real-time pupil tracking in highly off- axis images,

    L. ´Swirski, A. Bulling, and N. Dodgson, “Robust real-time pupil tracking in highly off- axis images,” in Proceedings of the Symposium on Eye Tracking Research and Applications. ACM, 2012, pp. 173–176

    work page 2012

  56. [56]

    A new kalman-filter-based framework for fast and accurate visual tracking of rigid objects,

    Y. Yoon, A. Kosaka, and A. C. Kak, “A new kalman-filter-based framework for fast and accurate visual tracking of rigid objects,” Robotics, IEEE Transactions on, vol. 24, no. 5, pp. 1238–1251, 2008

    work page 2008

  57. [57]

    Predictive head movement tracking using a kalman filter,

    A. Kiruluta, M. Eizenman, and S. Pasupathy, “Predictive head movement tracking using a kalman filter,” Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, vol. 27, no. 2, pp. 326–331, 1997

    work page 1997

  58. [58]

    Histograms of oriented gradients for human detection,

    N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Com- puter Vision and Pattern Recognition, IEEE Computer Society Conference on, vol. 1, 2005, pp. 886–893

    work page 2005

  59. [59]

    Facial feature detection and tracking with automatic template selection,

    D. Cristinacce and T. F. Cootes, “Facial feature detection and tracking with automatic template selection,” in Automatic Face and Gesture Recognition, 7th International Con- ference on. IEEE, 2006, pp. 429–434

    work page 2006

  60. [60]

    Fully automatic facial feature point detection using gabor feature based boosted classifiers,

    D. Vukadinovic and M. Pantic, “Fully automatic facial feature point detection using gabor feature based boosted classifiers,” in Systems, Man and Cybernetics, IEEE International Conference on, vol. 2, 2005, pp. 1692–1698

    work page 2005

  61. [61]

    Fast normalized cross-correlation,

    J. Lewis, “Fast normalized cross-correlation,” in Vision interface, vol. 10, no. 1, 1995, pp. 120–123. 132

    work page 1995

  62. [62]

    Tomasi and T

    C. Tomasi and T. Kanade, Detection and tracking of point features . School of Computer Science, Carnegie Mellon Univ. Pittsburgh, 1991

    work page 1991

  63. [63]

    Visible-spectrum gaze tracking for sports,

    B. Pires, M. Hwangbo, M. Devyver, and T. Kanade, “Visible-spectrum gaze tracking for sports,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2013, pp. 1005–1010

    work page 2013

  64. [64]

    Iris center corneal reflection method for gaze tracking using visible light,

    J. Sigut and S.-A. Sidha, “Iris center corneal reflection method for gaze tracking using visible light,” Biomedical Engineering, IEEE Transactions on, vol. 58, no. 2, pp. 411–419, 2011

    work page 2011

  65. [65]

    On estimating regression,

    E. A. Nadaraya, “On estimating regression,” Theory of Probability & Its Applications , vol. 9, no. 1, pp. 141–142, 1964

    work page 1964

  66. [66]

    Nonparametric regression using linear combinations of basis functions,

    R. Kohn, M. Smith, and D. Chan, “Nonparametric regression using linear combinations of basis functions,” Statistics and Computing , vol. 11, no. 4, pp. 313–322, 2001

    work page 2001

  67. [67]

    Active appearance models,

    T. F. Cootes, G. J. Edwards, and C. J. Taylor, “Active appearance models,” IEEE Trans- actions on Pattern Analysis & Machine Intelligence , vol. 23, no. 6, pp. 681–685, 2001

    work page 2001

  68. [68]

    Feature detection and tracking with constrained local models

    D. Cristinacce and T. F. Cootes, “Feature detection and tracking with constrained local models.” in Proceedings of the British Machine Vision Conference, vol. 2, no. 5, 2006, p. 6

    work page 2006

  69. [69]

    Robust real-time face detection,

    P. Viola and M. J. Jones, “Robust real-time face detection,” International journal of computer vision, vol. 57, no. 2, pp. 137–154, 2004

    work page 2004

  70. [70]

    Robust face detection using the hausdorff distance,

    O. Jesorsky, K. J. Kirchberg, and R. W. Frischholz, “Robust face detection using the hausdorff distance,” in Audio-and video-based biometric person authentication. Springer, 2001, pp. 90–95

    work page 2001

  71. [71]

    Bioid database,

    “Bioid database,” https://www.bioid.com/About/BioID-Face-Database/, accessed: 2015- 04-09

    work page 2015

  72. [72]

    Dataset for the evaluation of eye detector for gaze estimation,

    V. Ponz, A. Villanueva, and R. Cabeza, “Dataset for the evaluation of eye detector for gaze estimation,” in Proceedings of the ACM Conference on Ubiquitous Computing , 2012, pp. 681–684

    work page 2012

  73. [73]

    Burrus and T

    C. Burrus and T. W. Parks, DFT/FFT and Convolution Algorithms: theory and Imple- mentation. John Wiley & Sons, Inc., 1991

    work page 1991

  74. [74]

    The opencv library,

    G. Bradski et al., “The opencv library,” Doctor Dobbs Journal, vol. 25, no. 11, pp. 120–126, 2000

    work page 2000

  75. [75]

    ESCaF: Pupil Centre Localization Algorithm with Candidate Filtering

    A. George and A. Routray, “Escaf: Pupil centre localization algorithm with candidate filtering,” arXiv preprint arXiv:1807.10520 , 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  76. [76]

    Project glass: An extension of the self,

    T. Starner, “Project glass: An extension of the self,” Pervasive Computing, IEEE, vol. 12, no. 2, pp. 14–16, 2013

    work page 2013

  77. [77]

    Fovear: Combining an optically see- through near-eye display with projector-based spatial augmented reality,

    H. Benko, E. Ofek, F. Zheng, and A. D. Wilson, “Fovear: Combining an optically see- through near-eye display with projector-based spatial augmented reality,” in Proceedings of the 28th Annual ACM Symposium on User Interface Software & Technology . ACM, 2015, pp. 129–135

    work page 2015

  78. [78]

    Foveated 3d graphics,

    B. Guenter, M. Finch, S. Drucker, D. Tan, and J. Snyder, “Foveated 3d graphics,” ACM Transactions on Graphics, vol. 31, no. 6, p. 164, 2012. 133

    work page 2012

  79. [79]

    Evaluation of a low-cost open-source gaze tracker,

    J. San Agustin, H. Skovsgaard, E. Mollenbach, M. Barret, M. Tall, D. W. Hansen, and J. P. Hansen, “Evaluation of a low-cost open-source gaze tracker,” in Symposium on Eye- Tracking Research & Applications. ACM, 2010, pp. 77–80

    work page 2010

  80. [80]

    Pupil: an open source platform for pervasive eye tracking and mobile gaze-based interaction,

    M. Kassner, W. Patera, and A. Bulling, “Pupil: an open source platform for pervasive eye tracking and mobile gaze-based interaction,” inProceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct Publication . ACM, 2014, pp. 1151–1160

    work page 2014

Showing first 80 references.