We present an image-based method for face recognition across di#erent illumination and poses, where the term image-based means that no explicit prior 3D models are needed. As face recognition under illumination and pose variations involves three factors, namely identity, illumination, and pose, generalizations in all these three factors are desired. We present a recognition approach that is able to generalize in the identity and illumination dimensions and handle a given set of poses. Specifically, the proposed approach derives an identity signature that is illumination- and pose-invariant, where the identity is tackled using subspace encoding, the illumination is characterized using a Lambertian reflectance model, and the given set of poses is treated as a whole. Experimental results using the PIE database demonstrate the e#ectiveness of
|
1745
|
Eigenfaces for Recognition
– Turk, Pentland
- 1991
|
|
747
|
Light field rendering
– Levoy, Hanrahan
- 1996
|
|
600
|
The lumigraph
– Gortler, Grzeszczuk, et al.
- 1996
|
|
478
|
View-based and modular eigenspaces for face recognition
– Pentland, Moghaddam, et al.
- 1994
|
|
370
|
Application of the KarhunenLoeve Procedure for the Characterization of Human Faces
– Kirby
- 1990
|
|
313
|
Face Recognition: A Literature Survey
– Zhao, Chellappa, et al.
- 2000
|
|
184
|
The Visual Hull Concept for Silhouette-Based Image Understanding
– Laurentini
- 1994
|
|
170
|
Image-Based Visual Hulls
– Matusik, Buehler, et al.
- 2000
|
|
144
|
Linear object classes and image synthesis from a single example
– Vetter, Poggio
- 1997
|
|
136
|
From few to many: Illumination cone models for face recognition under variable lighting and pose
– Gheorghiades, Belhumeur, et al.
- 2001
|
|
133
|
T.: Automatic interpretation and coding of face images using flexible models
– Lanitis, Taylor, et al.
- 1997
|
|
131
|
Lambertian reflectance and linear subspaces
– Basri, Jacobs
- 2001
|
|
67
|
On Photometric Issues in 3D visual recognition from a single 2D
– Shashua
- 1997
|
|
59
|
Incremental singular value decomposition of uncertain data with missing values
– Brand
- 2002
|
|
49
|
Multilinear analysis of image ensembles: TensorFaces
– Vasilescu, Terzopoulos
- 2002
|
|
43
|
Determining generative models of objects under varying illumination: Shape and albedo from multiple images using SVD and integrability
– Yuille, Snow, et al.
- 1999
|
|
39
|
The quotient image: class based re-rendering and recognition with varying illuminations
– Riklin-Raviv, Shashua
- 1999
|
|
36
|
Learing bilinear models for two-factor problems in vision
– Freeman, Tenenbaum
- 1997
|
|
31
|
Eigen light-fields and face recognition across pose
– Gross, Matthews, et al.
- 2002
|
|
29
|
Efficient, robust and accurate fitting of a 3D morphable model
– Romdhani, Vetter
- 2003
|
|
19
|
Stochastic approximation and rate-distortion analysis for robust structure and motion estimation
– Chowdhury, Chellappa
- 2001
|
|
16
|
Characterization of human faces under illumination variations using rank, integrability, and symmetry constraints
– Zhou, Chellappa, et al.
- 2004
|
|
12
|
Fisher light-fields for face recognition across pose and illumination
– Gross, Matthews, et al.
- 2002
|
|
10
|
Face reconstruction from video using uncertainty analysis and a generic model
– Chowdhury, Chellappa
- 2003
|
|
7
|
The CMU pose, illuminatin, and expression (PIE) database
– Sim, Baker, et al.
- 2002
|
|
6
|
Regularized bundle adjustment to model heads from image sequences without calibrated data
– Fua
- 2000
|
|
6
|
Rank constrained recognition under unknown illumination
– Zhou, Chellappa
- 2003
|
|
5
|
Contour based 3d face modeling from a monocular video
– Gupta, Roy-Chowdhury, et al.
- 2004
|
|
3
|
Model-based bundle adjustment with applicaiton to face modeling
– Shan, Liu, et al.
- 2001
|
|
2
|
Face identification across di#erent poses and illumination with a 3D morphable model
– Blanz, Vetter
- 2003
|
|
2
|
Structure from motion using sequetial Monte Carlo methods
– Qian, Chellappa
- 2001
|
|
1
|
The FERET evaluaiton methodology for face-recognition algorithms
– Phillips, Moon, et al.
- 2000
|
