Abstract. We develop a face recognition algorithm which is insensitive to gross 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 direction lie in a 3-D linear subspace of the high dimensional feature space-- if the face is a Lambertian surface without self-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 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 significantly lower than those of the Eigenface technique when tested on the same database.
|
2961
|
Pattern Classification and Scene Analysis
– Duba, Hart
- 1973
|
|
1745
|
Eigenfaces for Recognition
– Turk, Pentland
- 1991
|
|
1094
|
Computer Vision
– Horn
- 1986
|
|
739
|
Visual learning and recognition of 3d objects from appearance
– Murase, Nayar
- 1995
|
|
496
|
The use of multiple measurements in taxonomic problems
– Fisher
- 1936
|
|
478
|
View-based and modular eigenspaces for face recognition
– Pentland, Moghaddam, et al.
- 1994
|
|
461
|
Face recognition using eigenfaces
– Turk, Pentland
- 1991
|
|
402
|
Human and Machine Recognition of faces: A survey
– Chellappa, Sirohey
- 1995
|
|
289
|
Low-dimensional procedure for the characterization of human faces
– Sirovich, Kirby
- 1987
|
|
205
|
Probabilistic visual learning for object detection
– Moghaddam, Pentland
- 1995
|
|
195
|
What is the set of images of an object under all possible lighting conditions
– Belhumeur, Kriegman
- 1996
|
|
182
|
Automatic Recognition and Analysis of Human Faces and Facial Expressions: A
– Samal
- 1992
|
|
159
|
Face recognition: the problem of compensating for changes in illumination direction
– Adini, Moses, et al.
- 1997
|
|
95
|
Face Recognition Under Varying Pose
– Beymer
- 1993
|
|
89
|
A low-dimensional representation of human faces for arbitrary lighting conditions
– Hallinan
- 1994
|
|
74
|
A unified approach to coding and interpreting face images
– Lanitis, Taylor, et al.
- 1995
|
|
61
|
Geometry and photometry in 3d visual recognition
– Shashua
- 1992
|
|
56
|
Face recognition: Features vs. templates
– Brunelli, Poggio
- 1993
|
|
51
|
Human and Machine Recognition of Faces: A
– Chellappa, Wilson, et al.
- 1995
|
|
46
|
Determining the gaze of faces in images
– Gee, Cipolla
- 1994
|
|
41
|
Finding face features
– Craw, Tock, et al.
- 1992
|
|
37
|
Analysing images of curved surfaces
– Woodham
- 1981
|
|
35
|
Determining Shape and Reflectance Using Multiple Images
– Silver
- 1980
|
|
34
|
A Deformable Model for Face Recognition Under Arbitrary Lighting Conditions
– Hallinan
- 1995
|
|
30
|
Learning-based hand sign recognition using SHOSLIF-M
– Cui, Swets, et al.
- 1995
|
|
29
|
Face detection by fuzzy pattern matching
– Chen, Wu, et al.
- 1995
|
|
24
|
Automatic recognition of human facial expressions
– Matsuno, Lee, et al.
- 1995
|
|
22
|
Finding faces in cluttered scenes using labelled random graph matching
– Leung, Burl, et al.
- 1995
|
|
19
|
Lowdimensional procedure for the characterization of human faces
– Sirovitch, Kirby
- 1987
|
|
16
|
A Real-Time Face Recognition System Using Custom VLSI Hardware
– Gilbert, Yang
- 1993
|
|
12
|
Determining the gaze of faces
– Gee, Cipolla
- 1994
|
|
11
|
Human face recognition method based on the statistical model of small sample size
– Cheng, Liu, et al.
- 1991
|
|
5
|
Learning-Based Hand Sign Recognition Using
– Cui, Swets, et al.
- 1995
|
|
5
|
Finding Faces
– Leung, Burl, et al.
- 1995
|
|
5
|
ªFace Recognition: Features vs
– Brunelli, Poggio
- 1993
|
|
4
|
Dimensionality of Illumination
– Nayar, Murase
- 1996
|
|
2
|
Eigenfaces vs. Fisherfaces: Recognition Using
– Belhumeur, Hespanha, et al.
- 1996
|
|
2
|
A Unified Approach to Coding and Interpreting
– Lanitis, Taylor, et al.
- 1995
|
|
2
|
Face Detection by Fuzzy
– Chen, Wu, et al.
- 1995
|
