by Bernd Heisele, Ý Purdy Ho, Þ Tomaso Poggio
In Proc. 8th International Conference on Computer Vision
http://www.ai.mit.edu/projects/cbcl/publications/ps/iccv2001.pdf
Add To MetaCart
Abstract:
We present a component-based method and two global methods for face recognition and evaluate them with respect to robustness against pose changes. In the component system we first locate facial components, extract them and combine them into a single feature vector which is classified by a Support Vector Machine (SVM). The two global systems recognize faces by classifying a single feature vector consisting of the gray values of the whole face image. In the first global system we trained a single SVM classifier for each person in the database. The second system consists of sets of viewpoint-specific SVM classifiers and involves clustering during training. We performed extensive tests on a database which included faces rotated up to about � Æ in depth. The component system clearly outperformed both global systems on all tests. 1.
Citations
|
4514
|
Statistical Learning Theory
– Vapnik
- 1998
|
|
982
|
Support-vector networks
– Cortes, Vapnik
- 1995
|
|
805
|
An algorithm for vector quantizer design
– Linde, Buzo, et al.
- 1980
|
|
739
|
Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection,” Proc
– Belhumeur, Hespanha, et al.
- 1997
|
|
461
|
Face recognition using eigenfaces
– Turk, Pentland
- 1991
|
|
402
|
Human and Machine Recognition of faces: A survey
– Chellappa, Sirohey
- 1995
|
|
399
|
Recognition: Features versus Template
– Brunelli, Poggio
- 1993
|
|
232
|
Krüger N, Malsburg C. Face recognition by elastic bunch graph matching
– Wiskott, Fellous
- 1997
|
|
148
|
Extracting support data for a given task
– Scholkopf, Burges, et al.
- 1995
|
|
133
|
T.: Automatic interpretation and coding of face images using flexible models
– Lanitis, Taylor, et al.
- 1997
|
|
124
|
Large margin DAGs for multiclass classification
– Platt, Cristianini, et al.
- 2000
|
|
107
|
Support Vector Machines for 3-D Object Recognition
– Pontil, Verri
- 1998
|
|
95
|
Face Recognition Under Varying Pose
– Beymer
- 1993
|
|
85
|
Beyond eigenfaces: Probabilistic matching for face recognition
– Moghaddam, Pentland
- 1998
|
|
51
|
Face detection in still gray images
– Heisele, Poggio, et al.
- 2000
|
|
47
|
Learning and Example Selection for Object and Pattern Recognition
– Sung
- 1995
|
|
45
|
Synthesis of novel views from a single face image
– Vetter
- 1998
|
|
33
|
Face recognition by Support Vector Machines
– Guo, Li, et al.
- 2000
|
|
29
|
Categorization of faces using unsupervised feature extraction
– Fleming, Cottrell
- 1990
|
|
20
|
Learning support vectors for face verification and recognition
– Jonsson, Matas, et al.
- 2000
|
|
20
|
M.Hayes, “An embedded hmm-based approach for face detection and recognition
– Nefian
- 1999
|
|
19
|
Lowdimensional procedure for the characterization of human faces
– Sirovitch, Kirby
- 1987
|
|
1
|
Person recognition in image sequences: The mit espresso machine system. submitted to
– Nakajima, Pontil, et al.
- 2000
|
