Back

In the Eye of the Beholder: A Survey of Models for Eyes and Gaze

D. HansenQ. Ji

article2010TPAMI1,569 citations

Presents a comprehensive survey of video-based eye detection, tracking, and gaze estimation techniques, comparing methods by their geometric properties and reported accuracies to guide researchers toward effective computer vision solutions for human-computer interaction.

Listen

Human eye movements provide critical insight into cognitive processes, user attention, and human-computer interaction. While early eye-tracking systems were highly intrusive—often requiring physical contact, bite bars, or cumbersome head-mounted apparatuses—modern video-based methods capture gaze remotely. However, building reliable, non-intrusive systems remains technically difficult due to substantial variations in eye physiology, eyelid occlusions, head movement, eyewear interference, and shifting ambient light conditions.

The main objective of the article is to provide a comprehensive survey and evaluation of video-based eye detection, tracking, and three-dimensional gaze estimation models. Specifically, it reviews the theoretical foundations, geometric properties, hardware setups, and operational accuracies of prevailing techniques across the literature.

To accomplish this, the authors conduct an extensive cross-comparative review of decades of computer vision and video-oculography research. The analysis categorizes eye detection into shape-based, appearance-based, feature-based, and hybrid models, while classifying gaze estimation into two-dimensional regression techniques and three-dimensional geometric models. The evaluation examines performance across diverse hardware configurations, including passive visible light, active infrared illumination, single-camera arrangements, and multi-camera stereo setups.

The findings indicate that active infrared illumination remains the standard for indoor systems because it produces distinct reflections (glints) and high contrast, but it struggles in outdoor environments and with eyeglasses. In gaze tracking, standard two-dimensional regression methods offer high accuracy (often below one degree) but fail when users move their heads. In contrast, three-dimensional geometric models effectively achieve head-pose invariance, with setups using a single camera and two infrared light sources emerging as a balanced, highly accurate choice (reporting errors typically between one and three degrees). While appearance-based methods bypass the need for explicit feature calibration, they require extensive training data and do not yet guarantee head-pose invariance.

These insights demonstrate a clear trade-off between deployment flexibility, setup cost, and user tolerance. Fully calibrated three-dimensional systems achieve high precision but require rigid hardware setups and costly specialized components, restricting them primarily to high-end diagnostic, research, or commercial tools. Conversely, low-cost consumer applications—such as assistive communication interfaces, automotive fatigue monitoring, and hands-free computing—require flexible, affordable designs that can operate using standard web cameras, even if baseline accuracy is modestly lower.

To advance the field, the authors recommend transitioning toward hybrid modeling frameworks that integrate feature geometry with appearance data. Research priorities must focus on reducing or eliminating user-specific calibration, improving tracking robustness under natural light without infrared dependencies, and developing specialized algorithms capable of handling eyewear distortions and significant head motion.

These conclusions should be considered in light of certain limitations across the reviewed literature. Reported accuracy figures vary widely depending on smoothing techniques, image resolution, and whether optical refraction through the cornea was modeled. Readers should note that current non-intrusive systems still exhibit degraded accuracy near display boundaries and under challenging lighting conditions.

biometric identificationscomputer visiondetection algorithmeye gaze trackinggaze modelseye models
Hansen et al (2010).pdf
  • Paper: Active Appearance Models Revisited, Iain Matthews et al. (2004). Active Appearance Models provide the core deformable shape-and-appearance fitting principles that foundationally underpin facial landmark tracking and feature-based eye region localization.
  • Paper: Camera Calibration with Distortion Models and Accuracy Evaluation, Juyang Weng et al. (1992). Understanding camera calibration and geometric lens distortion models is essential for mastering the optical and 3D geometric eye-tracking formulations analyzed in the survey.
  • Paper: Face Recognition Based on Fitting a 3D Morphable Model, Volker Blanz et al. (2003). This paper establishes the 3D morphable model framework necessary for understanding how 3D head-pose invariance and facial geometry recovery are achieved in gaze tracking.
  • Paper: Detecting Faces in Images: A Survey, Ming-Hsuan Yang et al. (2002). This comprehensive survey provides the foundational taxonomy of shape, appearance, and feature-based detection models that eye and gaze detection directly build upon.
  • Paper: A Model of Saliency-Based Visual Attention for Rapid Scene Analysis, Laurent Itti et al. (1998). This seminal work introduces computational visual saliency, providing the theoretical context for why human gaze fixation and eye movements are analyzed in vision systems.
  • Paper: The CMU Pose, Illumination, and Expression Database, Terence Sim et al. (2003). This benchmark details the multi-camera and multi-illumination datasets that established standardized evaluation for head pose, facial features, and gaze estimation.
  • Paper: Incremental Learning for Robust Visual Tracking, David A. Ross et al. (2008). This work establishes online appearance-based subspace tracking, a core technique utilized to maintain robust temporal tracking of eye and facial regions under appearance variations.
Cover for In the Eye of the Beholder: A Survey of Models for Eyes and Gaze

Abstract

Despite active research and significant progress in the last 30 years, eye detection and tracking remains challenging due to the individuality of eyes, occlusion, variability in scale, location, and light conditions. Data on eye location and details of eye movements have numerous applications, and are essential in face detection, biometric identification and particular human computer interaction tasks. This paper reviews current progress and state of the art in video-based eye detection and tracking, in order to identify promising techniques as well as issues to be further addressed. We present a detailed review of recent eye models and techniques for eye detection and tracking. We also survey methods for gaze estimation and compare them based on their geometric properties and reported accuracies. This review shows that despite their apparent simplicity, the development of a general eye detection technique involves addressing many challenges, requires further theoretical developments, and is consequently of interest to many other problems in computer vision and beyond.

Topics

biometric identificationscomputer visiondetection algorithmeye detectionhuman computer interaction

Keywords

eye gaze trackinggaze modelseye modelsgaze estimationeye localizationgaze direction measurement

Table of Contents

  • Index Terms
  • II. EYE MODELS FOR EYE DETECTION
  • A. Shape-based Approaches
  • B. Feature-Based Shape Methods
  • D. Hybrid Models
  • E. Other Methods
  • F. Discussion
  • III. GAZE ESTIMATION
  • FEATURE-BASED GAZE ESTIMATION
  • A. 2D Regression-based Gaze Estimation
  • B. 3D Model-based Gaze Estimation
  • B1: Single camera and single light
  • OTHER METHODS
  • IV. EYE DETECTION AND GAZE TRACKING APPLICATIONS
  • V. SUMMARY AND CONCLUSIONS
  • ACKNOWLEDGEMENTS
  • REFERENCES

Knowls

  1. Knowl 1 — Anatomical and Geometric Formulation of Eye Axes in Gaze Estimation

    model/method

    In video-oculographic gaze estimation, the human eye is geometrically modeled to determine the line of sight and the point of regard (PoR):

    • Anatomical Structures: The eyeball is approximated as a sphere with a radius of approximately 12−13 mm12 - 13\text{ mm}. The front of the eye features the transparent, curved cornea (with radius of curvature RcR_c), behind which lies the iris with a circular aperture (the pupil) of variable radius. The retina lines the interior back of the eyeball and contains the fovea, a small specialized region spanning approximately 2∘−5∘2^\circ - 5^\circ of the central visual field responsible for high-acuity vision.

    • Optical Axis (Line of Gaze, LoG): The line passing through the eyeball center ceye\mathbf{c}_{eye}, the corneal center of curvature cc\mathbf{c}_c (the nodal point), and the pupil center p\mathbf{p}.

    • Visual Axis (Line of Sight, LoS): The line connecting the fovea f\mathbf{f} and the corneal center of curvature cc\mathbf{c}_c. The visual axis represents the true direction of gaze.

    • Angular Discrepancy: The fovea does not lie exactly on the optical axis. In typical adults, the visual axis deviates from the optical axis by an offset angle of approximately 4∘−5∘4^\circ - 5^\circ horizontally (nasal direction) and 1.5∘1.5^\circ vertically (inferiorly), with inter-subject variation up to 3∘3^\circ.

    Both axes intersect at the corneal center cc\mathbf{c}_c. The point of regard is determined by finding the intersection of the 3D visual axis with the viewed scene surface (such as a computer monitor).

  2. Knowl 2 — Geometric Conditions for Head-Pose Invariance in 3D Model-Based Gaze Estimation

    theoretical result

    In 3D model-based gaze estimation, determining the gaze vector from 2D image measurements in a fully calibrated Euclidean coordinate system (calibrated camera intrinsics, light source positions, and monitor geometry) obeys specific minimal configuration constraints:

    1. Single Camera and Single Light Source: The 3D cornea center cc\mathbf{c}_c and 3D optical axis cannot be uniquely determined under unconstrained head movement. Head pose invariance is mathematically impossible from a single glint and pupil center alone unless additional constraints are enforced, such as fixing the head, fixing the eye-to-monitor distance, using anthropomorphic population averages, or utilizing the perspective deformation of the pupil ellipse.

    2. Single Camera and Multiple Light Sources (ge2\\ge 2 lights): If the corneal radius of curvature RcR_c is known, the 3D cornea center cc\mathbf{c}_c and 3D optical axis can be uniquely reconstructed from 2 or more corneal reflections (glints) and the pupil center. Determining the subject-specific visual axis requires only a single fixation calibration point to estimate the angular offset from the optical axis.

    3. Multiple (Stereo) Cameras and Multiple Light Sources: With two or more calibrated cameras and two or more light sources, the 3D cornea center cc\mathbf{c}_c and the optical axis can be directly calculated without prior knowledge of individual corneal curvature RcR_c and without requiring session calibration for the optical axis. Only one session calibration point is required to estimate the visual axis offset.

    4. Spherical Cornea Assumption: Most 3D model-based methods assume a spherical corneal surface. Deviations from sphericity at the periphery of the cornea cause geometric errors when gaze targets approach the extremities of a visual display.

  3. Knowl 3 — Active Infrared Differential Lighting for Pupil and Glint Detection

    model/method

    Active infrared (IR) illumination systems operate in the near-infrared spectrum (wavelengths λ≈780−880 nm\lambda \approx 780 - 880\text{ nm}), which are invisible to the human eye, avoid pupil constriction, and provide contrast invariant to ambient visible light.

    • On-Axis Illumination: An IR light source positioned close to the optical axis of the camera lens retro-reflects light off the retina back into the sensor, generating a bright pupil image (analogous to the red-eye effect).

    • Off-Axis Illumination: An IR light source positioned away from the camera's optical axis illuminates the eye without retinal retro-reflection reaching the sensor, generating a dark pupil image.

    • Differential Subtraction: By alternating between on-axis and off-axis IR sources on successive video frames (or employing multi-sensor setups with polarization filters), the difference image is formed:

    ΔI(x,y)=Ibright(x,y)−Idark(x,y)\Delta I(x,y) = I_{\text{bright}}(x,y) - I_{\text{dark}}(x,y)

    Thresholding ΔI(x,y)\Delta I(x,y) eliminates non-pupil background regions and isolates the pupil candidate blob.

    • Corneal Reflections (Glints): Specular reflections from the convex outer corneal surface form small, high-intensity virtual images (Purkinje reflections) that appear in both bright and dark pupil images, providing invariant spatial reference points.

  4. Knowl 4 — Cross-Ratio Projective Invariant Gaze Estimation

    model/method

    Cross-ratio gaze estimation allows determining the Point of Regard (PoR) on a computer monitor without requiring explicit 3D metric camera calibration:

    • Hardware Setup: Four coplanar infrared light sources are placed at the four corners of a rectangular display screen to project four virtual corneal reflections (glints) g1,g2,g3,g4\mathbf{g}_1, \mathbf{g}_2, \mathbf{g}_3, \mathbf{g}_4 onto the subject's eye, with an on-axis light source used to detect the pupil center p\mathbf{p}.

    • Projective Invariance: Under the assumption that the local corneal surface acts as a planar mirror and the glints are coplanar, the cross-ratio of points in projective geometry is invariant under perspective projection onto the camera image plane. The 2D position of the pupil center relative to the four glint positions in the image plane maps directly to the corresponding normalized coordinates on the monitor screen plane.

    • Correction and Calibration: Because the corneal surface is spherical rather than planar, and because the pupil is located in a different anatomical plane behind the cornea, non-linear displacements occur. Calibration parameters (either four individual corner parameters αi\alpha_i or a single global angular offset α\alpha) are learned while the user fixates on reference target points to correct for the offset between the Line of Sight (LoS) and Line of Gaze (LoG).

    • Limitation: The cross-ratio formulation does not maintain depth invariance; moving closer to or farther from the screen changes the projected visual-to-optical offset on the display.

  5. Knowl 5 — 2D Regression-Based Gaze Mapping and Head Motion Sensitivity

    model/method

    2D regression-based gaze estimation maps 2D extracted eye features directly to 2D display coordinates s=(xs,ys)T\mathbf{s} = (x_s, y_s)^T without reconstructing explicit 3D eye anatomy or calculating ray-surface intersections:

    • Feature Vector: The primary input is the pupil-glint displacement vector v=ppupil−pglint=(Δx,Δy)T\mathbf{v} = \mathbf{p}_{\text{pupil}} - \mathbf{p}_{\text{glint}} = (\Delta x, \Delta y)^T, occasionally augmented with pupil ellipse parameters (major/minor axes and orientation angle θ\theta).

    • Mapping Formulations: The mapping is approximated via parametric polynomials:

    xs=∑i,jaij(Δx)i(Δy)j,ys=∑i,jbij(Δx)i(Δy)jx_s = \sum_{i,j} a_{ij} (\Delta x)^i (\Delta y)^j, \quad y_s = \sum_{i,j} b_{ij} (\Delta x)^i (\Delta y)^j

    (typically second-order polynomials), or non-parametric regression methods including Generalized Regression Neural Networks (GRNN), Support Vector Regression (SVR), and Gaussian Process (GP) interpolation.

    • Head Motion Sensitivity: The fundamental limitation of single-camera 2D regression is its lack of head pose invariance. Because the eye rotates about the eyeball center ceye\mathbf{c}_{eye} while the glint is formed on the cornea centered at cc\mathbf{c}_c, eye rotation and head translation induce coupled non-linear shifts in v\mathbf{v}. Any significant head translation degrades calibration accuracy unless compensated by auxiliary sensors, stereo head tracking, or multiple glint reference arrays.

  6. Knowl 6 — Dual-Purkinje Image Gaze Tracking Principle

    model/method

    Purkinje images are optical reflections produced at the boundaries between media with differing refractive indices within the eye:

    • 1st Purkinje Image: Reflection from the anterior (outer) surface of the cornea (the standard corneal glint).
    • 2nd Purkinje Image: Reflection from the posterior (inner) surface of the cornea.
    • 3rd Purkinje Image: Reflection from the anterior surface of the crystalline lens.
    • 4th Purkinje Image: Reflection from the posterior surface of the crystalline lens (forming an inverted image).

    Decoupling Head Translation from Eyeball Rotation:

    1. When the eye translates laterally in space without rotating, the 1st and 4th Purkinje images undergo identical linear shifts in the image plane.
    2. When the eye rotates (changes gaze angle), the 1st and 4th Purkinje images move by different amounts and directions due to the different spatial depths and radii of curvature of the cornea and posterior lens surfaces.

    The vector difference between the 1st and 4th Purkinje reflection positions provides a direct measurement of angular eye orientation that is theoretically invariant to lateral head translation. Its practical limitation is the low intensity of the 4th Purkinje reflection, requiring high-intensity illumination and highly controlled lighting.

  7. Knowl 7 — Calibration Hierarchy in Video-Based Gaze Estimation

    definition

    Calibration in video-based eye tracking is categorized into four distinct procedural stages:

    1. Camera Calibration: Estimation of intrinsic camera parameters (focal length, principal point, pixel aspect ratio, and lens distortion coefficients).

    2. Geometric Calibration: Estimation of the relative 3D positions and orientations (extrinsic transformations) among system hardware components, including cameras, light sources, and display surfaces.

    3. Personal Calibration: Estimation of subject-specific anatomical and optical parameters of the eye, including corneal radius of curvature RcR_c, distance between pupil center and corneal center dpcd_{pc}, refractive index of the aqueous humor (n≈1.336n \approx 1.336), and the horizontal and vertical angular offsets (α,β\alpha, \beta) between the optical axis and visual axis.

    4. Gaze Mapping Calibration: Estimation of the numerical parameters or regression weights of the eye-to-gaze mapping function, typically acquired during an active session where the subject fixates on a predefined set of target points on a display.

  8. Knowl 8 — Performance and Configuration Comparison of Gaze Estimation Methods

    data/table

    The following table compares gaze estimation methods across camera count, light sources, estimated gaze metric (Point of Regard [PoR], Line of Gaze [LoG], or Line of Sight [LoS]), head pose invariance capability, geometric calibration requirements, and reported angular accuracies:

    Cameras Lights Gaze Info Head Pose Invariance Calibration Accuracy (deg) References
    1 0 PoR No None 2−4∘2 - 4^\circ [47], [46], [157]
    1 0 LoG/LoS No Fully 1−2∘1 - 2^\circ [151], [144], [145]
    1 0 LoG Approximate None <1∘< 1^\circ [79]
    1 1 PoR No None 1−2∘1 - 2^\circ [103], [156], [70]
    1 2 PoR Yes Fully 1−3∘1 - 3^\circ [105], [100], [43]
    1 + 1 (mirror) 1 PoR Yes Fully 3∘3^\circ [112]
    1 (+1) 4 PoR Yes None <1−2.5∘< 1 - 2.5^\circ [164], [20]
    2 0 PoR Yes None 1∘1^\circ [109]
    2 + 1 (pan/tilt) 1 LoG Yes None 0.7−1∘0.7 - 1^\circ [135]
    2 + 2 (mirrors) 2 PoR Yes Fully 0.6∘0.6^\circ [8]
    2 2 (3) PoR Yes Fully <1−2∘< 1 - 2^\circ [128], [127]
    3 2 PoR Yes Fully — [139], [11]
    1 1 PoR No None 0.5−1.5∘0.5 - 1.5^\circ [6], [133], [136], [160]

    Single-camera single-glint regression and appearance methods achieve 0.5∘−2∘0.5^\circ - 2^\circ accuracy under fixed head conditions but degrade under head movement. Fully calibrated 3D model-based systems utilizing ≥2\ge 2 lights or stereo cameras achieve head-pose invariant PoR estimation with accuracies between 0.6∘0.6^\circ and 3∘3^\circ. Projective cross-ratio methods with 4 lights achieve <1∘−2.5∘< 1^\circ - 2.5^\circ without explicit camera calibration.

  9. Knowl 9 — Taxonomy of Eye Detection and Localization Models

    model/method

    Video-based eye detection techniques are structured into four primary model paradigms based on geometric and photometric modeling:

    1. Shape-Based Approaches: Use geometric shape models of eye components.

      • Simple Elliptical Models: Model pupil or iris contours via 5-parameter ellipses using Hough transforms, voting schemes (gradient field accumulation, isophote curvature), or optimization (Daugman integrodifferential operator, Starburst radial search with RANSAC, EM/RANSAC contour likelihoods).
      • Complex Deformable Templates: Model eyelid boundaries via two parabolas (e.g., Yuille-Hallinan 11-parameter template) and circular iris boundaries, fitted through energy minimization combining valley, edge, peak, and internal elastic forces.

    2. Feature-Based Approaches: Extract discrete local photometric landmarks without fitting whole geometric templates.

      • Edge and line tracking using steerable Gabor filters.
      • Multi-layer perception micro-structure detection.
      • Fixed spatial relationship templates (such as circle-frequency filters on the 'between-the-eyes' region).
      • Variance projection functions for iris and eyelid boundary localization.

    3. Appearance-Based (Holistic) Approaches: Treat eye patches directly as photometric patterns in image or subspace representations.

      • Intensity template matching, Hidden Markov Models (HMM), and Support Vector Machines (SVM).
      • Subspace projection via Principal Component Analysis (Eigeneyes).
      • Multi-scale filter cascades (Wavelet Radial Basis Functions, cascaded Haar-like features trained with AdaBoost/GentleBoost, recursive non-parametric discriminant features).

    4. Hybrid Approaches: Integrate shape constraints with photometric appearance.

      • Active Appearance Models (AAM) and Constrained Local Models (CLM) combining linear shape deformations with texture eigenmodels.
      • Multi-cue systems combining color trackers (e.g., mean-shift) for coarse search with grayscale AAM or deformable templates for fine pupil/iris localization.

  10. Knowl 10 — Comparison of Eye Detection Models across Operating Conditions and Invariances

    data/table

    The following table summarizes the operational characteristics, light source compatibility, environmental invariances, and operational prerequisites of surveyed eye detection methods:

    Method Type Extracted Info Illumination Invariance Requirements
    Circular Shape Pupil IR Scale, Minor Head pose High res, High contrast
    Ellipse Shape Iris, Pupil Indoor, Outdoor, (IR) Head pose, Scale High contrast
    Ellipse Shape Pupil IR Head pose, Scale High contrast, Temporal tracking
    Complex Shape Pupil, Iris, Corners Indoor, Outdoor Partial Head pose, Scale High res, Good initialization
    Feature (Intensity) Iris, Corners, Pupil Indoor None High contrast
    Feature (Filter) Iris, Corners Indoor None High contrast
    Feature (Area) Between-Eyes Indoor Scale, Head pose, Occlusion None
    Appearance Entire Eye Indoor, Outdoor Partial Head pose, Partial Scale None
    Symmetry Iris, Pupil Sunlight / Visible Head pose, High contrast None
    Motion / Blink Entire Eye Indoor, Outdoor None Temporal frames
    Hybrid All Eye Features Indoor, Outdoor, IR Head pose, Scale Good initialization

    Methods relying on active IR illumination and simple shape fitting provide high pupil contrast indoors with low computational overhead, whereas complex deformable and hybrid active appearance models provide detailed eyelid/corner localization but require close initialization and higher image resolution.

Coverage note — Specific implementation details of cited historical algorithms (such as specific neural network layer dimensions or proprietary software drivers) and detailed taxonomies of end-user application domains (e.g., assistive typing versus marketing analysis) were omitted in favor of the survey's foundational contributions on geometric eye models, detection paradigms, and gaze tracking theory.

References

  1. 1.Javier San Agustin, Arantxa Villanueva, and Rafael Cabeza. Pupil brightness variation as a function of gaze direction. In ETRA '06: Proceedings of the 2006 symposium on Eye tracking research & applications, pages 49–49, New York, NY, USA, 2006. ACM Press.
  2. 2.A. Amir, L. Zimet, A. Sangiovanni-Vincentelli, and S. Kao. An embedded system for an eye-detection sensor. Computer Vision and Image Understanding, 98(1):104–123, 2005.
  3. 3.Geerd Anders. Pilot's attention allocation during approach and landing - eye- and head-tracking research. In 11th International Symposium on Aviation Psychology, 2001.
  4. 4.J. Bala, K. DeJong, J. Huang, H. Vafaie, and H. Wechsler. Visual routine for eye detection using hybrid genetic architectures. In Proc. of Interntional Conf. on Pattern Recognition, Vienna, Austria, 1996.
  5. 5.L.-P. Bala, K. Talmi, and J. Liu. Automatic detection and tracking of faces and facial features in video sequences. In Picture Coding Symposium 1997, Berlin Germany, September 1997.
  6. 6.Shumeet Baluja and Dean Pomerleau. Non-intrusive gaze tracking using artificial neural networks. In Jack D. Cowan, Gerald Tesauro, and Joshua Alspector, editors, Advances in Neural Information Processing Systems, volume 6, pages 753–760. Morgan Kaufmann Publishers, Inc., 1994.
  7. 7.P. Baudisch, Doug DeCarlo, Andrew T. Duchowski, and Wilson S. Geisler. Focusing on the essential: considering attention in display design. Commun. ACM, 46(3):60–66, 2003.
  8. 8.D. Beymer and M. Flickner. Eye gaze tracking using an active stereo head. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, volume II, pages 451–458, 2003.
  9. 9.Guido Boening, Klaus Bartl, Thomas Dera, Stanislavs Bardins, Erich Schneider, and Thomas Brandt. Mobile eye tracking as a basis for real-time control of a gaze driven head-mounted video camera. In ETRA '06: Proceedings of the 2006 symposium on Eye tracking research & applications, pages 56–56, New York, NY, USA, 2006. ACM Press.
  10. 10.R. Bolt. Gaze-orchestrated dynamic windows. In SIGGRAPH '81: Proceedings of the 8th annual conference on Computer graphics and interactive techniques, pages 109–119, New York, NY, USA, 1981. ACM Press.
  11. 11.Xavier L C Brolly and Jeffrey B Mulligan. Implicit calibration of a remote gaze tracker. In Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW '04), volume 8, page 134, 2004.
  12. 12.Roger H.S. Carpenter. Movements of the Eyes. Pion Limited, London, 1988.
  13. 13.G. Chow and X. Li. Towards a system for automatic facial feature detection. Pattern Recognition, 26:1739–1755, 1993.
  14. 14.http://www.cogain.org/. COGAIN, 2007.
  15. 15.C. Colombo and A. del Bimbo. Real-time head tracking from the deformation of eye contours using a piecewise affine camera. PRL, 20(7):721–730, July 1999.
  16. 16.D. Comaniciu, V. Ramesh, and P. Meer. Kernel-based object tracking. IEEE Trans. Pattern Analysis and Machine Intelligence, 25(5):564–577, 2003.
  17. 17.T. F. Cootes, G. J. Edwards, and C. J. Taylor. Active appearance models. In Proc. European Conf. on Computer Vision, volume 2, pages 484–498. Springer, 1998.
  18. 18.T. F. Cootes and Taylor. Active shape models – 'smart snakes'. In Proc. British Machine Vision Conf., BMVC92, pages 266–275, 1992.
  19. 19.J. Coughlan, A. Yuille, C. English, and D. Snow. Efficient deformable template detection and localization without user initialization. Computer Vision and Image Understanding, 78(3):303–319, 2000.
  20. 20.Flávio Luiz Coutinho and Carlos Hitoshi Morimoto. Free head motion eye gaze tracking using a single camera and multiple light sources. In Manuel Menezes de Oliveira Neto and Rodrigo Lima Carceroni, editors, Proceedings. IEEE Computer Society, 8–11 Oct. 2006 2006.
  21. 21.H. Crane and C. Steele. Accurate three-dimensional eye tracker. Journal of Optical Society of America, 17(5):691–705, 1978.
  22. 22.D. Cristinacce and T. Cootes. Feature detection and tracking with constrained local models. In 17th British Machine Vision Conference, Edinburgh, UK, pages 929–938, 2006.
  23. 23.J.L. Crowley and F. Berard. Multi-modal tracking of faces for video communications. Computer Vision and Pattern Recognition, 1997. Proceedings., 1997 IEEE Computer Society Conference on, pages 640–645, 1997.
  24. 24.J. Daugman. The importance of being random: statistical principles of iris recognition. Pattern Recognition, 36(2):279–291, 2003.
  25. 25.J. Deng and F. Lai. Region-based template deformation and masking for eye-feature extraction and description. Pattern Recognition, 30:403–419, 1997.
  26. 26.T. D'Orazio, M. Leo, G. Cicirelli, and A Distante. An algorithm for real time eye detection in face images. Proceedings of the 17th International Conference on Pattern Recognition, 3(0):278–281, 2004.
  27. 27.Detlev Droege, Carola Schmidt, and Deitrich Paulus. A comparison of pupil centre estimation algorithms. In Howell Istance, Olga Stepankova, and Richard Bates, editors, COGAIN 2008 - Communication, Environment and mobility Control by Gaze, pages 23–26, 2008.
  28. 28.A. Duchowski. Eye Tracking Methodology: Theory and Practice. Springer-Verlag New York, Inc., Secaucus, NJ, USA, 2003.
  29. 29.Andrew T. Duchowski, Eric Medlin, Nathan Cournia, Anand Gramopadhye, Brian Melloy, and Santosh Nair. 3d eye movement analysis for vr visual inspection training. In ETRA '02: Proceedings of the 2002 symposium on Eye tracking research & applications, pages 103–110, New York, NY, USA, 2002. ACM.
  30. 30.Y. Ebisawa. Improved video-based eye-gaze detection method. IEEE Transcations on Instrumentation and Measruement, 47(2):948–955, 1998.
  31. 31.Y. Ebisawa and S. Satoh. Effectiveness of pupil area detection technique using two light sources and image difference method. In Proceedings of the 15th Annual Int. Conf. of the IEEE Eng. in Medicine and Biology Society, pages 1268–1269, San Diego, CA, 1993.
  32. 32.Yoshinobu Ebisawa. Realtime 3d position detection of human pupil. Virtual Environments, Human-Computer Interfaces and Measurement Systems, 2004. (VECIMS). 2004 IEEE Symposium on, pages 8–12, 2004.
  33. 33.G.J. Edwards, T. F. Cootes, and C. J. Taylor. Face recognition using active appearance models. In ECCV'98. 5th European Conf. on Computer Vision. Proc., volume 2, pages 581–95. Springer-Verlag, 1998.
  34. 34.A. Tomono et al. Pupil extraction processing and gaze point detection system allowing head movement. Trans. of the institute of electronics, information, and communication engineers of Japan, J76-D-II(3), 1993.
  35. 35.I. R. Fasel, B. Fortenberry, and J. R. Movellan. A generative framework for real time object detection and classification. Computer Vision and Image Understanding, 98(1):182–210, April 2005.
  36. 36.G. C. Feng and P. C. Yuen. Variance projection function and its application to eye detection for human face recognition. International Journal of Computer Vision, 19:899–906, 1998.
  37. 37.G. C. Feng and P. C. Yuen. Multi-cues eye detection on gray intensity image. Pattern recognition, 34:1033–1046, 2001.
  38. 38.Rogerio Schmidt Feris, Teofilo Emidio de Campos, and Roberto Marcondes Cesar Junior. Detection and tracking of facial features in video sequences. In Proceedings of Medical Image Computing and Computer-Assisted Intervention, pages 127–135, 2000.
  39. 39.V. Di Gesu and C. Valenti. Symmetry operators in computer vision. Vistas Astronomy, 40(4):461–468, 1996.
  40. 40.Y. Gofman and N Kiryati. Detecting symmetry in gray level images: The global optimization approach. In Proc. Int. Conf. on Pattern Recognition, 1996.
  41. 41.J. H. Goldberg and A. M. Wichansky. Eye tracking in usability evaluation: A practitioner's guide, pages 493–516. Elsevier Science, Amsterdam, 2003.
  42. 42.K. Grauman, M. Betke, J. Gips, and G.R. Bradski. Communication via eye blinks: Detection and duration analysis in real time. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pages I:1010–1017, 2001.
  43. 43.Elias Daniel Guestrin and Moshe Eizenman. General theory of remote gaze estimation using the pupil center and corneal reflections. IEEE Transactions on Biomedical Engineering, 53(6):1124–1133, 2006.
  44. 44.P. W. Hallinan. Recognizing human eyes. In SPIE Proceedings,Vol. 1570: Geometric Methods in Computer Vision, pages 212–226, 1991.
  45. 45.D. Witzner Hansen. Comitting Eye Tracking. PhD thesis, IT University of Copenhagen, 2003.
  46. 46.D. Witzner Hansen, J. P. Hansen, M. Nielsen, A. S. Johansen, and M. B. Stegmann. Eye typing using markov and active appearance models. In IEEE Workshop on Applications on Computer Vision, pages 132–136, 2003.
  47. 47.D. Witzner Hansen and A. E.C. Pece. Eye tracking in the wild. Computer Vision and Image Understanding, 98(1):182–210, April 2005.
  48. 48.Dan Witzner Hansen. Using Colors for Eye Tracking, chapter Color Image Processing: Emerging Applications, pages 309–327. CRC Press.
  49. 49.Dan Witzner Hansen and Riad Hammoud. An improved likelihood model for eye tracking. Computer Vision and Image Understanding, In Press:1–1, 1-1 2007.
  50. 50.Dan Witzner Hansen and John Paulin Hansen. Robustifying eye interaction. In 2. Conference on Vision for Human Computer Interaction, pages 152–158, 2006.
  51. 51.Dan Witzner Hansen, Henrik H. T. Skovsgaard, John Paulin Hansen, and Emilie Møllenbach. Noise tolerant selection by gaze-controlled pan and zoom in 3d. In ETRA '08: Proceedings of the 2008 symposium on Eye tracking research & applications, pages 205–212, New York, NY, USA, 2008. ACM.
  52. 52.J. P. Hansen, K. Itoh, A. S. Johansen, K. Tørning, and A. Hirotaka. Gaze typing compared with input by head and hand. In Eye Tracking Research & Applications Symposium 2004, pages 131 – 138. ACM, 2004.
  53. 53.A. Haro, M. Flickner, and I. Essa. Detecting and tracking eyes by using their physiological properties, dynamics, and appearance. In Proceedings IEEE CVPR 2000, Hilton Head Island, South Carolina, 2000.
  54. 54.J. Heinzmann and A. Zelinsky. 3-d facial pose and gaze point estimation using a robust real-timetracking paradigm. In IEEE International Conference on Automatic Face and Gesture Recognition, 1998.
  55. 55.Craig Hennessey, Borna Noureddin, and Peter Lawrence. A single camera eye-gaze tracking system with free head motion. In Proceedings of Eye Tracking Research & Applications (ETRA), pages 87–94, 2006.
  56. 56.Craig Hennesy and Peter Lawrence. 3d point-of-gaze estimation on a volumetric display. In roceedings of the 2008 symposium on Eye tracking research and applications, 2008.
  57. 57.R. Herpers, M. Michaelis, K. Lichtenauer, and G. Sommer. Edge and keypoint detection in facial regions. In International Conference on Automatic Face and Gesture-Recognition, pages 212–217, 1996.
  58. 58.P.M. Hillman, J.M. Hannah, and P.M. Grant. Global fitting of a facial model to facial features for model-based video coding. Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the 3rd International Symposium on, 1:359–364, 2003.
  59. 59.J. Huang, D Ii, X. Shao, and H. Wechsler. Pose discrimination and eye detection using support vector machines (svms). In Proceeding of NATO-ASI on Face Recognition: From Theory to Applications, pages 528–536, 1998.
  60. 60.J. Huang and H. Wechsler. Eye location using genetic algorithms. In 2nd Int'l conference in Audio and Video-Based Biometric Person Authentication (AVBPA), Washington, DC, USA, 1999.
  61. 61.Jeffrey Huang and Harry Wechsler. Eye detection using optimal wavelet packets and radial basis functions (rbfs). International Journal of Pattern recognition and Artificial Intelligence, 13(7), 1999.
  62. 62.T. E. Hutchinson. Human-computer interaction using eye-gaze input. IEEE Tran. on Systems, man, and cybernetics, 19(6), 1989.
  63. 63.K. Hyoki, M. Shigeta, N. Tsuno, Y. Kawamuro, and T. Kinoshita. Quantitative electro-oculography and electroencaphalography as indices of alertness. Electroencaphalography and Clinical Neurophysiology, 106:213–219, 1998.
  64. 64.A. Hyrskykari, P. Majaranta, A. Aaltonen, and K.-J. Raiha. Design issues of iDict: a gaze-assisted translation aid. In Proceedings of the symposium on Eye tracking research & applications 2000, pages 9–14, 2000.
  65. 65.A. Hyrskykari, P. Majaranta, and K.-J. Raiha. Proactive response to eye movements. In Matthias Rauterberg, Marino Menozzi, and Janet Wesson, editors, INTERACT '03: IFIP TC13 International Conference on Human-Computer Interaction, pages 129–136, Amsterdam, 2003. IOS Press.
  66. 66.A. Hyrskykari, P. Majaranta, and K.-J. Raiha. From gaze control to attentive interfaces. In Proceedings of the 11th International Conference on Human-Computer Interaction (HCII 2005). IOS Press, 2005.
  67. 67.Takahiro Ishikawa, Simon Baker, Iain Matthews, and Takeo Kanade. Passive driver gaze tracking with active appearance models. In Proceedings of the 11th World Congress on Intelligent Transportation Systems, October 2004.
  68. 68.J. P. Ivins and J. Porrill. A deformable model of the human iris for measuring small 3-dimensional eye movements. Machine Vision and Applications, 11(1):42–51, 1998.
  69. 69.Qiang Ji and Xiaojie Yang. Real-time eye, gaze, and face pose tracking for monitoring driver vigilance. Real-Time Imaging, 8(5):357–377, 2002.
  70. 70.Qiang Ji and Zhiwei Zhu. Eye and gaze tracking for interactive graphic display. In Proceedings of the 2nd international symposium on Smart graphics, pages 79–85, 2002.
  71. 71.M. Kampmann and L. Zhang. Estimation of eye, eyebrow and nose features in videophone sequences. In International Workshop on Very Low Bitrate Video Coding (VLBV 98), Urbana, USA, 1998.
  72. 72.Jeffrey J. Kang, Elias D. Guestrin, and Erez Eizenman. Investigation of the cross-ratio method for point-of-gaze estimation. Transactions on Biometical Engineering, accepted(x):xx–yy, mm 2008.
  73. 73.Faisal Karmali and Mark Shelhamer. Compensating for camera translation in video eye movement recordings by tracking a landmark selected automatically by a genetic algorithm. Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, pages 5298–5301 and 4029752, 2006.
  74. 74.S. Kawato and N. Tetsutani. Detection and tracking of eyes for gaze-camera control. In VI02, page 348, 2002.
  75. 75.Shinjiro Kawato and Jun Ohya. Real-time detection of nodding and head-shaking by directly detecting and tracking the between-eyes. In Proc. IEEE 4th Int. Conf. on Automatic Face and Gesture Recognition, pages 40–45, 2000.
  76. 76.Shinjiro Kawato and Jun Ohya. Two-step approach for real-time eye tracking with a new filtering technique. In Proc. Int. Conf. on System, Man & Cybernetics, pages 1366–1371, 2000.
  77. 77.Shinjiro Kawato and Nobuji Tetsutani. Detection and tracking of eyes for gaze-camera control. In Proc. of 15th International Conference on Vision Interface, 2002.
  78. 78.Shinjiro Kawato and Nobuji Tetsutani. Real-time detection of between-the-eyes with a circle frequencey filter. In Proc. of Asian Conference of Computer Vision 2002, volume II, pages 442–447, 2002.
  79. 79.Kyung-Nam Kim and R. S. Ramakrishna. Vision-based eye-gaze tracking for human computer interface. IEEE International Conf. on Systems, Man, and Cybernetics, 1999.
  80. 80.Soochan Kim and Qiang Ji. Non-intrusive eye gaze tracking under natural head movements. In 26th Annual International Conference IEEE Engineering in Medicine and Biology, Sept. 2004.
  81. 81.C. Kimme, D. Ballard, and J. Sklansky. Finding circles by an array of accumulators. Communications of ACM, 18(2):120–122, Feb 1975.
  82. 82.I. King and L. Xu. Localized principal component analysis learning for face feature extraction and recognition. In Proceedings to the Workshop on 3D Computer Vision, pages 124–128, Shatin, Hong Kong, 1997.
  83. 83.Susan M. Kolakowski and Jeff B. Pelz. Compensating for eye tracker camera movement. In ETRA '06: Proceedings of the 2006 symposium on Eye tracking research & applications, pages 79–85, 2006.
  84. 84.R. Kothari and J.L. Mitchell. Detection of eye locations in unconstrained visual images. Image Processing, 1996. Proceedings., International Conference on, 3:519–522, 1996.
  85. 85.Peter Kovesi. Symmetry and asymmetry from local phase. In Proc.10th Australian Joint Conf. Artificial Intelligence, pages 185–190, 1997.
  86. 86.K. Lam and H. Yan. Locating and extracting the eye in human face images. Pattern Recognition, 29:771–779, 1996.
  87. 87.C. Lankford. Effective eye-gaze input into windows. In Eye Tracking Research & Applications Symposium 2000 (ETRA'O0), pages 23–27, 2000.
  88. 88.J. L. Levine. An eye-controlled computer. Technical Report RC-8857, IBM Thomas J. Watson Research Center, Yorktown Heights, N.Y, 1982.
  89. 89.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 Proceedings of the Vision for Human-Computer Interaction Workshop, IEEE Computer Vision and Pattern Recognition Conference, 2005.
  90. 90.C.-C. Lin and W.-C. Lin. Extracting facial features by an inhibitory mechanism based on gradient distribution. Pattern Recognition, 29(12):2079–2101, 1996.
  91. 91.P. J. Locher and C. F. Nodine. Symmetry Catches The Eye. Eye Movements – From Physiology to Cognition, pages 353–361, 1987.
  92. 92.P. J. Locher and C. F. Nodine. The Perceptual Value of Symmetry. Computers and Mathematics with Applications, 17:475–484, 1989.
  93. 93.G. Loy and A. Zelinsky. Fast radial symmetry for detecting points of interest. PAMI, pages 959–973, August 2003.
  94. 94.B. D. Lucas and T. Kanade. An iterative image registration technique with an application to stereo vision. In International Joint Conference on Artificial Intelligence, 1981.
  95. 95.P. Majaranta and K.-J. Raiha. Twenty years of eye typing: systems and design issues. In ETRA '02: Proceedings of the symposium on Eye tracking research & applications, pages 15–22, New York, NY, USA, 2002. ACM Press.
  96. 96.T. Marui and Y. Ebisawa. Eye searching technique for video-based eye-gaze detection. Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE, 2:744–747, 1998.
  97. 97.Y. Matsumoto, T. Ogasawara, and A. Zelinsky. Behaviour recognition based on head pose and gaze direction measurement. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 2127–2132, 2000.
  98. 98.Y. Matsumoto and A. Zelinsky. An algorithm for real-time stereo vision implementation of head pose and gaze direction measurement. In International Conference on Automatic Face and Gesture Recognition, pages 499–504, 2000.
  99. 99.J. Merchant, R. Morrissette, and J. Porterfield. Remote measurements of eye direction allowing subject motion over one cubic foot of space. IEEE Transactions on Biomedical Engineering, 21(4), 1972.
  100. 100.André Meyer, Martin Böhme, Thomas Martinetz, and Erhardt Barth. A single-camera remote eye tracker. In Perception and Interactive Technologies, volume 4021 of Lecture Notes in Artificial Intelligence, pages 208–211. Springer, 2006.
  101. 101.J.M Miller, H.L. Hall, J.E Greivenkamp, and D.L. Guyton. Quantification of the bruckner test for strabismus. Invesigation Ophthalmology & Visual Science, 36(4):897–905, 1995.
  102. 102.Wei min Huang and Robert Mariani. Face detection and precise eyes location. In Proceedings of the International Conference on Pattern Recognition (ICPR'00), 2000.
  103. 103.C. H. Morimoto, D. Koons, A. Amir, and M. Flickner. Pupil detection and tracking using multiple light sources. Image and vision computing, 18(4):331–335, 2000.
  104. 104.C. H. Morimoto and M.R.M. Mimica. Eye gaze tracking techniques for interactive applications. Computer Vision and Image Understanding, 98(1):4–24, April 2005.
  105. 105.Carlos Morimoto, A. Amir, and M. Flickner. Detecting eye position and gaze from a single camera and 2 light sources. In International Conference on Pattern Recognition, 2002.
  106. 106.C.H. Morimoto and M. Flickner. Real-time multiple face detection using active illumination. In Proc. of the 4th IEEE International Conference on Automatic Face and Gesture Recognition 2000, Grenoble, France, 2000.
  107. 107.C.H. Morimoto, D. Koons, A. Amir, and M. Flickner. Pupil detection and tracking using multiple light sources. Technical Report RJ-10117, IBM Almaden Research Center, 1998.
  108. 108.P. Müller, D. Cavegn, G. d'Ydewalle, and R. Groner. A comparison of a new limbus tracker, corneal reflection technique, purkinje eye tracking and electro-oculography. In G. d'Ydewalle andJ. V. Rensbergen, editor, Perception and Cognition, pages 393–401. Elsevier Science Publishers, 1993.
  109. 109.R. Newman, Y. Matsumoto, S. Rougeaux, and A. Zelinsky. Real-time stereo tracking for head pose and gaze estimation. In International Conference on Automatic Face and Gesture Recognition, pages 122–128, 2000.
  110. 110.Karlene Nguyen, Cindy Wagner, David Koons, and Myron Flickner. Differences in the infrared bright pupil response of human eyes. In ETRA '02: Proceedings of the symposium on Eye tracking research & applications, pages 133–138, New York, NY, USA, 2002. ACM Press.
  111. 111.M. Nixon. Eye spacing measurement for facial recognition. In Proceedings of the Society of Photo-Optical Instrument Engineers, 1985.
  112. 112.B. Noureddin, P.D. Lawrence, and C.F. Man. A non-contact device for tracking gaze in a human computer interface. Computer Vision and Image Understanding, 98(1):52–82, 2005.
  113. 113.Takehido Ohno and Naoki Mukawa. A free-head, simple calibration, gaze tracking system that enables gaze-based interaction. In Eye Tracking Research & Applications Symposium 2004, pages 115 – 122, 2004.
  114. 114.Takehiko Ohno. One-point calibration gaze tracking method. In ETRA '06: Proceedings of the 2006 symposium on Eye tracking research & applications, pages 34–34, New York, NY, USA, 2006. ACM Press.
  115. 115.Takehiko Ohno, Naoki Mukawa, and Atsushi Yoshikawa. Freegaze: A gaze tracking system for everyday gaze interaction. In Symposium on ETRA 2002: Eye Tracking Research Applications Symposium, New Orleans, Louisiana, pages 125–132, 2002.
  116. 116.K.R. Park, J.J. Lee, and J. Kim. Facial and eye gaze detection. In Biologically Motivated Computer Vision, page 368, 2002.
  117. 117.A. Pentland, B. Moghaddam, and T. Starner. View-based and modular eigenspaces for face recognition. In Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'94), Seattle, WA, June 1994.
  118. 118.A. Perez, M.L. Cordoba, A. Garcia, R. Mendez, M.L. Munoz, J.L. Pedraza, and F. Sanchez. A precise eye-gaze detection and tracking system. Journal of WSCG, pages 105–8, 2003.
  119. 119.K. Rayner, C. Rotello, C. Steward, A. Keir, and A. Duffy. When looking at print advertisements. Journal of Experimental Psychology:Applied, 7(3):219–226, 2001.
  120. 120.M. Reinders, R. Koch, and J. Gerbrands. Locating facial features in image sequences using neural networks. In Proceedings of the Second International Conference on Automatic Face and Gesture Recognition, Killington, USA, 1997.
  121. 121.D. Reisfeld and Y. Yeshurun. Robust detection of facial features by generalized symmetry. In Proc. Int. Conf. on Pattern Recognition, pages I:117–120, 1992.
  122. 122.Arrington Reseach. http://www.arringtonresearch.com, 2007.
  123. 123.RPI. http://www.ecse.rpi.edu/homepages/cvrl/database/database.html, 2008.
  124. 124.Ferdinando Samaria and Steve Young. Hmm-based architecture for face identification. Image Vision Comput., 12(8):537–543, 1994.
  125. 125.D. Scott and J. Findlay. Visual search, eye movements and display units. Human factors report, 1993.
  126. 126.G. Sela and M.D. Levine. Real-time attention for robotic vision. Real-Time Imaging, 3:173–194, 1997.
  127. 127.S.-W. Shih and J Liu. A novel approach to 3-D gaze tracking using stereo cameras. IEEE Transactions on Systems, Man and Cybernetics, 34(1):234–245, Feb 2004.
  128. 128.Sheng-Wen Shih, Yu-Te Wu, and Jin Liu. A calibration-free gaze tracking technique. In Proceedings of the 15th International Conference on Pattern Recognition, pages 201–204, 2000.
  129. 129.S. Sirohey, A. Rosenfeld, and Z. Duric. A method of detecting and tracking irises and eyelids in video. Pattern Recognition, 35(6):1389–1401, June 2002.
  130. 130.Saad A. Sirohey and Azriel Rosenfeld. Eye detection in a face image using linear and nonlinear filters. Pattern recognition, 34:1367–1391, 2001.
  131. 131.Dave M. Stampe. Heuristic filtering and reliable calibration methods for video-based pupil-traking systems. Behaviour Research Methods, Instruments & Computers, 25(2):137–142, 1993.
  132. 132.R. Stiefelhagen, J. Yang, and A. Waibel. A model-based gaze tracking system. In Proceedings of IEEE International Joint Symposia on Intelligence and Systems, pages 304–310, 1996.
  133. 133.Rainer Stiefelhagen, Jie Yang, and Alex Waibel. Tracking eyes and monitoring eye gaze. In Proceedings of the Workshop on Perceptual User Interfaces, pages 98–100, 1997.
  134. 134.Akira Sugioka, Yoshinobu Ebisawa, and Masao Ohtani. Noncontact video-based eye-gaze detection method allowing large head displacements. Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings, 2:526–528, 1996.
  135. 135.Kay Talmi and Jin Liu. Eye and gaze tracking for visually controlled interactive stereoscopic displays. Signal Processing: Image Communication, 14(10):799–810, 1999.
  136. 136.Kar-Han Tan, D.J. Kriegman, and N. Ahuja. Appearance-based eye gaze estimation. Applications of Computer Vision, 2002. (WACV 2002). Proceedings. Sixth IEEE Workshop on, pages 191–195, 2002.
  137. 137.J. H. Ten Kate, E. E. E. Frietman, W. Willems, B. M. Ter Haar Romeny, and E. Tenkink. Eye-switch controlled communication aids. In Proceedings of the 12th International Conference on Medical & Biological Engineering, 1979.
  138. 138.Yingli Tian, T. Kanade, and J. F. Cohn. Dual-state parametric eye tracking. In Proceedings of the 4th IEEE International Conference on Automatic Face and Gesture Recognition, 2000.
  139. 139.A. Tomono, M. Iida, and Y. Kobayashi. A tv camera system which extracts feature points for non-contact eye movement detection. In SPIE Optics, Illumination, and Image Sensing for Machine Vision, volume 1194, pages 2 – 12, 1989.
  140. 140.D. Tweed and T. Vilis. Geometric relations of eye position and velocity vectors during saccades. Vision Research, 30(1):111–127, 1990.
  141. 141.Geoffrey Underwood. Cognitive Processes in Eye Guidance. Oxford University Press, 2005.
  142. 142.Roberto Valenti and Theo Gevers. Accurate eye center location and tracking using isophote curvature. In Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2008.
  143. 143.R. Vertegaal, I. Weevers, and C. Sohn. GAZE-2: an attentive video conferencing system. In CHI '02: Extended abstracts on Human factors in computing systems, pages 736–737, New York, NY, USA, 2002. ACM Press.
  144. 144.A. Villanueva, R. Cabeza, and S. Porta. Eye tracking: Pupil orientation geometrical modeling. Image and Vision Computing, 24(7):663–679, July 2006.
  145. 145.A. Villanueva, R. Cabeza, and S. Porta. Gaze tracking system model based on physical parameter. International Journal on Pattern Recognition and Artificial Intelligence, In press, 2007.
  146. 146.Arantxa Villanueva and Rafael Cabeza. Models for gaze tracking systems. volume 2007, page Article ID 23570, 2007.
  147. 147.P. Viola and M. Jones. Robust real-time face detection. In Proc. Int. Conf. on Computer Vision, page II: 747, 2001.
  148. 148.R. Wagner and H.L Galiana. Evaluation of three template matching algorithms for registering images of the eye. In IEEE Tras. Biomed. Eng., volume 12, pages 1313–1319, 1992.
  149. 149.J. Waite and J.M. Vincent. A probabilistic framework for neural network facial feature location. British Telecom Technology Journal, 10(3):20–29, 1992.
  150. 150.J. G. Wang and E. Sung. Gaze determination via images of irises. Image and Vision Computing, 19(12):891–911, 2001.
  151. 151.J. G. Wang, E. Sung, and R. Venkateswarlu. Estimating the eye gaze from one eye. Computer Vision and Image Understanding, 98(1):83–103, April 2005.
  152. 152.Peng Wang, M.B. Green, Qiang Ji, and J. Wayman. Automatic eye detection and its validation. Computer Vision and Pattern Recognition, 2005 IEEE Computer Society Conference on, 3:164–164, 2005.
  153. 153.Peng Wang and Qiang Ji. Learning discriminant features for multi-view face and eye detection. Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 1:373–379, 2005.
  154. 154.D. J. Ward and D. J. C. MacKay. Fast hands-free writing by gaze direction. Nature, 418(6900):838, 2002.
  155. 155.M. Wedel and R. Peiters. Eye fixations on advertisments and memory for brands: A model and findings. Marketing Science, 19(4):297–312, 2000.
  156. 156.Jr. White, K.P., T.E. Hutchinson, and J.M. Carley. Spatially dynamic calibration of an eye-tracking system. IEEE Transactions on Systems, Man, and Cybernetics, 23(4):1162–1168, 1993.
  157. 157.Oliver M. C. Williams, Andrew Blake, and Roberto Cipolla. Sparse and semi-supervised visual mapping with the s3p. In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2006), 17-22 June 2006, New York, NY, USA, pages 230–237, 2006.
  158. 158.X. Xie, R. Sudhakar, and H. Zhuang. On mproving eye feature-extraction using deformable templates. Pattern Recognition, 27(6):791–799, June 1994.
  159. 159.X. Xie, R. Sudhakar, and H. Zhuang. A cascaded scheme for eye tracking and head movement compensation. IEEE Trans. Systems, Man, and Cybernetics, A28:487–490, 1998.
  160. 160.L.Q. Xu, D. Machin, and P. Sheppard. A novel approach to real-time non-intrusive gaze finding. In Proc. British Machine Vision Conference, 1998.
  161. 161.H. Yamazoe, A. Utsumi, T. Yonezawa, and S. Abe. Remote gaze estimation with a single camera based on facial-feature tracking without special calibration actions. In Proceedings of the 2008 symposium on Eye tracking research and applications, pages 140–145, 2008.
  162. 162.J. Yang, R. Stiefelhagen, U. Meier, and A. Waibel. Real-time face and facial feature tracking and applications. In Proceedings of AVSP'98, pages 79–84, Terrigal, Australia, 1998.
  163. 163.A. Yarbus. Eye Movements and Vision. in Plenum Press, 1967.
  164. 164.D. H. Yoo and M. J. Chung. A novel non-intrusive eye gaze estimation using cross-ratio under large head motion. Computer Vision and Image Understanding, 98(1):25–51, April 2005.
  165. 165.David Young, Hilary Tunley, and Richard Samuels. Specialised hough transform and active contour methods for real-time eye tracking. Technical Report 386, School of Cognitive and Computing Sciences, University of Sussex, 1995.
  166. 166.A. Yuille, P. Hallinan, and D. Cohen. Feature extraction from faces using deformable templates. International Journal of Computer Vision, 8(2):99–111, 1992.
  167. 167.L. Zhang. Estimation of eye and mouth corner point positions in a knowledge-based coding system. In Proc. SPIE Vol 2952, pages 21–18, Berlin, Germany, 1996.
  168. 168.Z. Zhu, K. Fujimura, and Q. Ji. Real-time eye detection and tracking under various light conditions. Eye Tracking Research and Applications Symposium, 25-27 March, New Orleans, LA, USA, 2002.
  169. 169.Z. Zhu, Q. Ji, and K. Fujimura. Combining kalman filtering and mean shift for real time eye tracking. In Proc. Int. Conf. on Pattern Recognition, pages IV: 318–321, 2002.
  170. 170.Zhiwei Zhu and Qiang Ji. Novel eye gaze tracking techniques under natural head movement. IEEE Transactions on Biomedical Engineering, 54(12):2246–60, 2007.
  171. 171.Zhiwei Zhu, Qiang Ji, and K.P. Bennett. Nonlinear eye gaze mapping function estimation via support vector regression. Pattern Recognition, 2006. ICPR 2006. 18th International Conference on, 1:1132–1135, 2006.

Citation

MLA
Hansen, D. W., and Qiang Ji. “In the Eye of the Beholder: A Survey of Models for Eyes and Gaze”. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 3, 2010, pp. 478–500, https://doi.org/10.1109/TPAMI.2009.30.
APA
Hansen, D. W., & Qiang Ji. (2010). In the Eye of the Beholder: A Survey of Models for Eyes and Gaze. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(3), 478–500. https://doi.org/10.1109/TPAMI.2009.30
Chicago
Hansen, D. W., and Qiang Ji. 2010. “In the Eye of the Beholder: A Survey of Models for Eyes and Gaze”. IEEE Transactions on Pattern Analysis and Machine Intelligence 32 (3): 478–500. https://doi.org/10.1109/TPAMI.2009.30.
Harvard
Hansen, D.W. and Qiang Ji (2010) “In the Eye of the Beholder: A Survey of Models for Eyes and Gaze”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(3), pp. 478–500. Available at: https://doi.org/10.1109/TPAMI.2009.30.
Vancouver
1. Hansen DW, Qiang Ji (2010) In the Eye of the Beholder: A Survey of Models for Eyes and Gaze. IEEE Transactions on Pattern Analysis and Machine Intelligence 32:478–500

BibTeX

@article{Hansen_2010, title={In the Eye of the Beholder: A Survey of Models for Eyes and Gaze}, volume={32}, ISSN={0162-8828}, url={http://dx.doi.org/10.1109/TPAMI.2009.30}, DOI={10.1109/tpami.2009.30}, number={3}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, publisher={Institute of Electrical and Electronics Engineers (IEEE)}, author={Hansen, D.W. and Qiang Ji}, year={2010}, month=Mar, pages={478–500} }
Metadata:Crossref

Access the Paper

This paper is available from its original source. Click below to access the PDF.

Open PDF