From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose

@article{Georghiades2001FromFT,
  title={From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose},
  author={Athinodoros S. Georghiades and Peter N. Belhumeur and David J. Kriegman},
  journal={IEEE Trans. Pattern Anal. Mach. Intell.},
  year={2001},
  volume={23},
  pages={643-660}
}
We present a generative appearance-based method for recognizing human faces under variation in lighting and viewpoint. Our method exploits the fact that the set of images of an object in fixed pose, but under all possible illumination conditions, is a convex cone in the space of images. Using a small number of training images of each face taken with different lighting directions, the shape and albedo of the face can be reconstructed. In turn, this reconstruction serves as a generative model… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 2,873 CITATIONS

Data-Driven Image Restoration

VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Noise-Resilient Sparse Subspace Clustering Algorithm for Image Sequences

  • 2017 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)
  • 2017
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Scheming an efficient facial recognition system using global and random local feature extraction methods

  • 2017 International Conference on Computer Science and Engineering (UBMK)
  • 2017
VIEW 12 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

EyeLHM: Real-Time Vision-Based approach for Eye Localization and Head Motion Estimation

  • 2016 International Conference on Autonomous Robot Systems and Competitions (ICARSC)
  • 2016
VIEW 9 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

General type-2 fuzzy edge detector applied on face recognition system using neural networks

  • 2016 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)
  • 2016
VIEW 6 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2001
2020

CITATION STATISTICS

  • 419 Highly Influenced Citations

  • Averaged 213 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 76 REFERENCES

From few to many: generative models for recognition under variable pose and illumination

  • Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580)
  • 2000
VIEW 4 EXCERPTS

The bas-relief ambiguity

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Illumination cones for recognition under variable lighting: faces

  • Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231)
  • 1998
VIEW 5 EXCERPTS

Eigenfaces vs

P. N. Belhumeur, J. P. Hespanha, D. J. Kriegman
  • Fisherfaces: Recognition using class specific linear projection. IEEE Trans. Pattern Anal. Mach. Intelligence, 19(7):711–720,
  • 1997
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Probabilistic Visual Learning for Object Representation

  • IEEE Trans. Pattern Anal. Mach. Intell.
  • 1997
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Visual learning and recognition of 3-d objects from appearance

  • International Journal of Computer Vision
  • 1995
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

A low-dimensional representation of human faces for arbitrary lighting conditions

  • 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition
  • 1994
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Eigenfaces for Recognition

  • Journal of Cognitive Neuroscience
  • 1991
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL