Download:
by Bernd Heisele, Thomas Serre, Massimiliano Pontil, Thomas Vetter, Tomaso Poggio
in NIPS
http://graphics.informatik.uni-freiburg.de/././publications/nips01.component.pdf
Add To MetaCart
Abstract:
We describe an algorithm for automatically learning discriminative parts in object images with SVM classifiers. It is based on growing image parts by minimizing theoretical bounds on the error probability of an SVM. Component-based face classifiers are then combined in a second stage to yield a hierarchical SVM classifier. Experimental results in face classification show considerable robustness for rotations in depth and suggest performance at significantly better level than other face detection systems. Novel aspects of our approach are: a) an algorithm to learn from examples component-based classification experts and their combination, b) the use of 3D morphable models for training and c) a MAX operation – on the output of each component classifier within a search region – which may be relevant for biological models of visual recognition. 1
Citations
|
4514
|
Statistical Learning Theory
– Vapnik
- 1998
|
|
231
|
A statistical method for 3D object detection applied to faces and cars
– Schneiderman, Kanade
- 2000
|
|
152
|
Hierarchical models of object recognition in cortex. Nat Neurosci 2
– Riesenhuber, Poggio
- 1999
|
|
129
|
Example-based object detection in images by components
– Mohan, Papageorgiou, et al.
|
|
124
|
Probabilistic modeling of local appearance and spatial relationships for object recognition
– Schneiderman, Kanade
- 1998
|
|
106
|
Rotation invariant neural network-based face detection
– Rowley, Baluja, et al.
- 1998
|
|
104
|
T.: A trainable system for object detection
– Papageorgiou, Poggio
- 2000
|
|
84
|
Finding faces in cluttered scenes using random labeled graph matching
– Leung, Burl, et al.
- 1995
|
|
76
|
The CMU pose, illumination, and expression (PIE) database
– Sim, Baker, et al.
- 2002
|
|
70
|
A network that learns to recognize 3Dobjects. Nature 343
– Poggio, Edelman
- 1990
|
|
58
|
and T.Poggio, “Face Recognition with Support Vector Machines: Global versus Component-based Approach,” ICCV
– Heisele
- 2001
|
|
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
|
|
35
|
Original approach for the localisation of objects in images
– Vaillant, Monrocq, et al.
- 1994
|
|
28
|
Feature reduction and hierarchy of classifiers for fast object detection in video images
– Heisele, Serre, et al.
- 2001
|
|
26
|
A cluster-based statistical model for object detection
– Rikert, Jones, et al.
- 1999
|
|
19
|
Object classification using a fragment-based representation
– Ullman, Sali
- 2000
|
|
10
|
Feature selection for support vector machines
– Weston, Mukherjee, et al.
- 2001
|
|
5
|
Towards automatic dscovery of object categories
– Weber, Welling, et al.
- 2000
|
