Skip to content

Latest commit

 

History

History
63 lines (57 loc) · 3.9 KB

1996-eigenfaces-vs-fisherfaces-recognition-using-class-specific-linear-projection.md

File metadata and controls

63 lines (57 loc) · 3.9 KB
title authors fieldsOfStudy meta_key numCitedBy reading_status ref_count tags urls venue year
Eigenfaces vs. Fisherfaces - Recognition Using Class Specific Linear Projection
P. Belhumeur
J. Hespanha
D. Kriegman
Computer Science
1996-eigenfaces-vs-fisherfaces-recognition-using-class-specific-linear-projection
11746
TBD
50
gen-from-ref
other-default
paper
ECCV
1996

semanticscholar url

Eigenfaces vs. Fisherfaces - Recognition Using Class Specific Linear Projection

Abstract

We develop a face recognition algorithm which is insensitive to large variation in lighting direction and facial expression. Taking a pattern classification approach, we consider each pixel in an image as a coordinate in a high-dimensional space. We take advantage of the observation that the images of a particular face, under varying illumination but fixed pose, lie in a 3D linear subspace of the high dimensional image space-if the face is a Lambertian surface without shadowing. However, since faces are not truly Lambertian surfaces and do indeed produce self-shadowing, images will deviate from this linear subspace. Rather than explicitly modeling this deviation, we linearly project the image into a subspace in a manner which discounts those regions of the face with large deviation. Our projection method is based on Fisher's linear discriminant and produces well separated classes in a low-dimensional subspace, even under severe variation in lighting and facial expressions. The eigenface technique, another method based on linearly projecting the image space to a low dimensional subspace, has similar computational requirements. Yet, extensive experimental results demonstrate that the proposed "Fisherface" method has error rates that are lower than those of the eigenface technique for tests on the Harvard and Yale face databases.

Paper References

  1. Eigenfaces for Recognition
  2. Face Recognition - The Problem of Compensating for Changes in Illumination Direction
  3. Human face recognition method based on the statistical model of small sample size
  4. View-based and modular eigenspaces for face recognition
  5. Face recognition under varying pose
  6. A unified approach to coding and interpreting face images
  7. Dimensionality of illumination in appearance matching
  8. Automatic recognition of human facial expressions
  9. A low-dimensional representation of human faces for arbitrary lighting conditions
  10. Face detection by fuzzy pattern matching
  11. Human and machine recognition of faces - a survey
  12. Automatic recognition and analysis of human faces and facial expressions - a survey
  13. Determining the gaze of faces in images
  14. A real-time face recognition system using custom VLSI hardware
  15. Finding faces in cluttered scenes using random labeled graph matching
  16. Analysing Images of Curved Surfaces
  17. Face Recognition - Features Versus Templates
  18. What is the set of images of an object under all possible lighting conditions?
  19. Pattern rejection
  20. Probabilistic visual learning for object detection
  21. Low-dimensional procedure for the characterization of human faces.
  22. Finding Face Features
  23. Learning-based hand sign recognition using SHOSLIF-M
  24. Geometry and Photometry in 3D Visual Recognition
  25. Determining Shape and Reflectance Using Multiple Images
  26. Pattern classification and scene analysis
  27. Computer Vision
  28. THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS
  29. Computer Vision
  30. Finding Faces in Cluttered Scenes Using Labeled Random Graph Matching.
  31. Recognition using class specific linear projection