Object class recognition by unsupervised scale-invariant learning

R. Fergus; P. Perona; A. Zisserman

Object class recognition by unsupervised scale-invariant learning

R. Fergus, P. Perona, A. Zisserman

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and relative scale. An entropy-based feature detector is used to select regions and their scale within the image. In learning the parameters of the scale-invariant object model are estimated. This is done using expectation-maximization in a maximum-likelihood setting. In recognition, this model is used in a Bayesian manner to classify images. The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).

Original language	English (US)
Title of host publication	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	2
State	Published - 2003
Event	2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Madison, WI, United States Duration: Jun 18 2003 → Jun 20 2003

Other

Other	2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Country/Territory	United States
City	Madison, WI
Period	6/18/03 → 6/20/03

ASJC Scopus subject areas

Computer Vision and Pattern Recognition
Software
Control and Systems Engineering
Electrical and Electronic Engineering

Cite this

@inproceedings{6da26d38a9ab43b8aa10989420c237f1,

title = "Object class recognition by unsupervised scale-invariant learning",

abstract = "We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and relative scale. An entropy-based feature detector is used to select regions and their scale within the image. In learning the parameters of the scale-invariant object model are estimated. This is done using expectation-maximization in a maximum-likelihood setting. In recognition, this model is used in a Bayesian manner to classify images. The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).",

author = "R. Fergus and P. Perona and A. Zisserman",

year = "2003",

language = "English (US)",

volume = "2",

booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

note = "2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition ; Conference date: 18-06-2003 Through 20-06-2003",

}

TY - GEN

T1 - Object class recognition by unsupervised scale-invariant learning

AU - Fergus, R.

AU - Perona, P.

AU - Zisserman, A.

PY - 2003

Y1 - 2003

N2 - We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and relative scale. An entropy-based feature detector is used to select regions and their scale within the image. In learning the parameters of the scale-invariant object model are estimated. This is done using expectation-maximization in a maximum-likelihood setting. In recognition, this model is used in a Bayesian manner to classify images. The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).

AB - We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constellations of parts. A probabilistic representation is used for all aspects of the object: shape, appearance, occlusion and relative scale. An entropy-based feature detector is used to select regions and their scale within the image. In learning the parameters of the scale-invariant object model are estimated. This is done using expectation-maximization in a maximum-likelihood setting. In recognition, this model is used in a Bayesian manner to classify images. The flexible nature of the model is demonstrated by excellent results over a range of datasets including geometrically constrained classes (e.g. faces, cars) and flexible objects (such as animals).

UR - http://www.scopus.com/inward/record.url?scp=0041940256&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0041940256&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0041940256

VL - 2

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

T2 - 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

Y2 - 18 June 2003 through 20 June 2003

ER -

Object class recognition by unsupervised scale-invariant learning

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this