Appearance-based eye gaze estimation

Kar Han Tan, D. J. Kriegman, N. Ahuja

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We present a method for estimating eye gaze direction, which represents a departure from conventional eye gaze estimation methods, the majority of which are based on tracking specific optical phenomena like corneal reflection and the Purkinje images. We employ an appearance manifold model, but instead of using a densely sampled spline to perform the nearest manifold point query, we retain the original set of sparse appearance samples and use linear interpolation among a small subset of samples to approximate the nearest manifold point. The advantage of this approach is that since we are only storing a sparse set of samples, each sample can be a high dimensional vector that retains more representational accuracy than short vectors produced with dimensionality reduction methods. The algorithm was tested with a set of eye images labelled with ground truth point-of-regard coordinates. We have found that the algorithm is capable of estimating eye gaze with a mean angular error of 0.38 degrees, which is comparable to that obtained by commercially available eye trackers.

Original languageEnglish (US)
Title of host publicationProceedings - 6th IEEE Workshop on Applications of Computer Vision, WACV 2002
PublisherIEEE Computer Society
Number of pages5
ISBN (Electronic)0769518583
StatePublished - 2002
Event6th IEEE Workshop on Applications of Computer Vision, WACV 2002 - Orlando, United States
Duration: Dec 3 2002Dec 4 2002

Publication series

NameProceedings of IEEE Workshop on Applications of Computer Vision
ISSN (Print)2158-3978
ISSN (Electronic)2158-3986


Other6th IEEE Workshop on Applications of Computer Vision, WACV 2002
Country/TerritoryUnited States


  • Application software
  • Deformable models
  • Displays
  • Gray-scale
  • Humans
  • Interpolation
  • Iris
  • Optical reflection
  • Spline
  • Vectors

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications


Dive into the research topics of 'Appearance-based eye gaze estimation'. Together they form a unique fingerprint.

Cite this