Sensitivity to variations in illumination is a fundamental and challenging problem in face recognition. In this paper, we describe a new method based on symmetric shape-from-shading (SFS) to develop a face recognition system that is robust to changes in illumination. The basic idea of this approach is to use the symmetric SFS algorithm as a tool to obtain a prototype image which is illumination-normalized. Applying traditional SFS algorithms to real images of complex objects (in terms of their shape and albedo variations) such as faces is very challenging. It is shown that the symmetric SFS algorithm has a unique point-wise solution. In practice, given a single real face image with complex shape and varying albedo, even the symmetric SFS algorithm cannot guarantee the recovery of accurate and complete shape information. For the particular problem of face recognition, we utilize the fact that all faces share a similar shape making the direct computation of the prototype image from a given face image feasible. The symmetry property has been used to develop a new model-based source-from-shading algorithm which is more accurate than existing algorithms. Using the symmetric property, we are also able to gain insight into how changes in illumination affect eigen-subspace based face recognition systems. Finally, to demonstrate the efficacy of our method, we have applied it to several publicly available face databases. We first compare a new illumination-invariant measure to the measure proposed in (Jacobs et al., 1998), and then demonstrate significant performance improvement over existing face recognition systems using PCA and/or LDA for images acquired under variable lighting conditions.
|
1745
|
Eigenfaces for Recognition
– Turk, Pentland
- 1991
|
|
739
|
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,” Proc
– Belhumeur, Hespanha, et al.
- 1997
|
|
704
|
Curves and Surfaces for Computer Aided Geometric Design, 4th ed.Academic
– Farin
- 1997
|
|
427
|
Probabilistic visual learning for object representation
– Moghaddam, Pentland
- 1997
|
|
402
|
Human and Machine Recognition of faces: A survey
– Chellappa, Sirohey
- 1995
|
|
356
|
The FERET Evaluation Methodology for Face-Recognition Algorithms
– Phillips, Moon, et al.
- 2000
|
|
337
|
EigenTracking: Robust matching and tracking of articulated objects using a view-based representation
– Black, Jepson
- 1998
|
|
320
|
Robust Statistics: The Approach Based On Influence Functions
– Hampel, Ronchetti, et al.
- 1986
|
|
289
|
Low-dimensional procedure for the characterization of human faces
– Sirovich, Kirby
- 1987
|
|
263
|
Using discriminant eigenfeatures for image retrieval
– Swets, Weng
- 1996
|
|
211
|
Eds.Shapefrom Shading
– Horn, Brooks
- 1989
|
|
195
|
What is the set of images of an object under all possible lighting conditions
– Belhumeur, Kriegman
- 1996
|
|
159
|
Face recognition: the problem of compensating for changes in illumination direction
– Adini, Moses, et al.
- 1997
|
|
153
|
Photometric method for determining surface orientation from multiple images
– Woodham
- 1980
|
|
144
|
Ill-posed problems in early vision
– Bertero, Poggio, et al.
- 1988
|
|
137
|
Sclaro . Closed-form solutions for physically based shape modeling and recognition
– Pentland, Stan
- 1991
|
|
133
|
Numerical shape from shading and occluding boundaries, Artif. Intell
– Ikeuchi, Horn
|
|
132
|
Face recognition by elastic bunch graph matching
– Wiskott, Fellous, et al.
- 1997
|
|
124
|
Discriminant Analysis for Recognition of Human Face Images
– Etemad, Chellappa
- 1997
|
|
108
|
Discriminant analysis of principal components for face recognition
– Zhao, Krishnaswamy, et al.
- 1998
|
|
89
|
A low-dimensional representation of human faces for arbitrary lighting conditions
– Hallinan
- 1994
|
|
88
|
Surface Reflection: Physical and Geometric Perspectives”, Carnegie Mellon University technical report
– Nayar, Ikeuchi, et al.
- 1989
|
|
81
|
Estimation of illuminant direction, albedo, and shape from shading
– Zheng, Chellappa
- 1991
|
|
69
|
Illumination cones for recognition under variable lighting: Faces
– Georghiades, Belhumeur, et al.
- 1998
|
|
67
|
On Photometric Issues in 3D visual recognition from a single 2D
– Shashua
- 1997
|
|
62
|
Redlich, “Statistical approach to shape from shading: Reconstruction of 3D face surfaces from single 2D images,” Neural Comput
– Atick, Griffin, et al.
- 1996
|
|
62
|
A.: Improved Methods of Estimating Shape from Shading Using the Light Source Coordinate System
– Lee, Rosenfeld
- 1985
|
|
53
|
Physics-based Deformable Models: Applications to Computer Vision, Graphics and Medical Imaging
– Metaxas
- 1996
|
|
53
|
Finding the Illuminant Direction
– Pentland
- 1982
|
|
53
|
Subspace linear discriminant analysis for face recognition
– Zhao, Chellappa, et al.
- 1999
|
|
44
|
Probabilistic Solution of Inverse Problems
– Marroquin
- 1985
|
|
39
|
Algebraic tools for the performance evaluation of discrete event systems
– Cohen, Moller, et al.
- 1989
|
|
36
|
Comparing Images Under Variable Illumination
– JACOBS, BELHUMEUR, et al.
- 1998
|
|
35
|
A feature based approach to face recognition
– Manjunath, Chellappa, et al.
- 1992
|
|
34
|
Direct method for reconstructing shape from shading
– Dupuis, Oliensis
- 1991
|
|
31
|
The Eikonal equation: Some results applicable to computer vision,“J
– Bruss
- 1982
|
|
27
|
Integrability disambiguates surface recovery in two-image photometric stereo
– Onn, Bruckstein
- 1990
|
|
18
|
A practical guide to splines
– Boor
- 1978
|
|
16
|
Cycle times and fixed points of min-max functions
– Gunawardena
- 1994
|
|
15
|
On the existence of cycle times for some nonexpansive maps
– Gunawardena, Keane
- 1995
|
|
13
|
The duality theorem for min-max functions
– Gaubert, Gunawardena
- 1998
|
|
13
|
Some ergodic results on stochastic iterative discrete events systems
– Vincent
- 1997
|
|
13
|
A Fast Linear Shape from Shading
– Tsai, Shah
- 1992
|
|
13
|
Face Recognition: From Theory to Applications
– Wechsler, Phillips, et al.
- 1998
|
|
12
|
Finite Element
– Bathe
- 1982
|
|
12
|
Parametric shape-from-shading by radial basis functions
– Wei, Hirzinger
- 1997
|
|
11
|
Min-max functions
– Gunawardena
- 1994
|
|
10
|
Ergodic theorems for stochastic operators and discrete event networks
– Baccelli, Mairesse
- 1995
|
|
10
|
Dimensionality of illumination manifolds in eigenspace
– Nayar, Murase
- 1994
|
|
9
|
A non-linear hierarchy for discrete event dynamical systems
– Gaubert, Gunawardena
- 1998
|
|
