Mixtures of trees for object recognition

Sergey Ioffe, David Forsyth

Research output: Contribution to journalConference article

Abstract

Efficient detection of objects in images is complicated by variations of object appearance due to intra-class object differences, articulation, lighting, occlusions, and aspect variations. To reduce the search required for detection, we employ the bottom-up approach where we find candidate image features and associate some of them with parts of the object model. We represent objects as collections of local features, and would like to allow any of them to be absent, with only a small subset sufficient for detection; furthermore, our model should allow efficient correspondence search. We propose a model, Mixture of Trees, that achieves these goals. With a mixture of trees, we can model the individual appearances of the features, relationships among them, and the aspect, and handle occlusions. Independences captured in the model make efficient inference possible. In our earlier work, we have shown that mixtures of trees can be used to model objects with a natural tree structure, in the context of human tracking. Now we show that a natural tree structure is not required, and use a mixture of trees for both frontal and view-invariant face detection. We also show that by modeling faces as collections of features we can establish an intrinsic coordinate frame for a face, and estimate the out-of-plane rotation of a face.

Original languageEnglish (US)
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2
StatePublished - Dec 1 2001
Externally publishedYes
Event2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Kauai, HI, United States
Duration: Dec 8 2001Dec 14 2001

Fingerprint

Object recognition
Face recognition
Lighting

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Mixtures of trees for object recognition. / Ioffe, Sergey; Forsyth, David.

In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, 01.12.2001.

Research output: Contribution to journalConference article

@article{4e80bbda82a34f3994ae8caf04bc170b,
title = "Mixtures of trees for object recognition",
abstract = "Efficient detection of objects in images is complicated by variations of object appearance due to intra-class object differences, articulation, lighting, occlusions, and aspect variations. To reduce the search required for detection, we employ the bottom-up approach where we find candidate image features and associate some of them with parts of the object model. We represent objects as collections of local features, and would like to allow any of them to be absent, with only a small subset sufficient for detection; furthermore, our model should allow efficient correspondence search. We propose a model, Mixture of Trees, that achieves these goals. With a mixture of trees, we can model the individual appearances of the features, relationships among them, and the aspect, and handle occlusions. Independences captured in the model make efficient inference possible. In our earlier work, we have shown that mixtures of trees can be used to model objects with a natural tree structure, in the context of human tracking. Now we show that a natural tree structure is not required, and use a mixture of trees for both frontal and view-invariant face detection. We also show that by modeling faces as collections of features we can establish an intrinsic coordinate frame for a face, and estimate the out-of-plane rotation of a face.",
author = "Sergey Ioffe and David Forsyth",
year = "2001",
month = "12",
day = "1",
language = "English (US)",
volume = "2",
journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
issn = "1063-6919",
publisher = "IEEE Computer Society",

}

TY - JOUR

T1 - Mixtures of trees for object recognition

AU - Ioffe, Sergey

AU - Forsyth, David

PY - 2001/12/1

Y1 - 2001/12/1

N2 - Efficient detection of objects in images is complicated by variations of object appearance due to intra-class object differences, articulation, lighting, occlusions, and aspect variations. To reduce the search required for detection, we employ the bottom-up approach where we find candidate image features and associate some of them with parts of the object model. We represent objects as collections of local features, and would like to allow any of them to be absent, with only a small subset sufficient for detection; furthermore, our model should allow efficient correspondence search. We propose a model, Mixture of Trees, that achieves these goals. With a mixture of trees, we can model the individual appearances of the features, relationships among them, and the aspect, and handle occlusions. Independences captured in the model make efficient inference possible. In our earlier work, we have shown that mixtures of trees can be used to model objects with a natural tree structure, in the context of human tracking. Now we show that a natural tree structure is not required, and use a mixture of trees for both frontal and view-invariant face detection. We also show that by modeling faces as collections of features we can establish an intrinsic coordinate frame for a face, and estimate the out-of-plane rotation of a face.

AB - Efficient detection of objects in images is complicated by variations of object appearance due to intra-class object differences, articulation, lighting, occlusions, and aspect variations. To reduce the search required for detection, we employ the bottom-up approach where we find candidate image features and associate some of them with parts of the object model. We represent objects as collections of local features, and would like to allow any of them to be absent, with only a small subset sufficient for detection; furthermore, our model should allow efficient correspondence search. We propose a model, Mixture of Trees, that achieves these goals. With a mixture of trees, we can model the individual appearances of the features, relationships among them, and the aspect, and handle occlusions. Independences captured in the model make efficient inference possible. In our earlier work, we have shown that mixtures of trees can be used to model objects with a natural tree structure, in the context of human tracking. Now we show that a natural tree structure is not required, and use a mixture of trees for both frontal and view-invariant face detection. We also show that by modeling faces as collections of features we can establish an intrinsic coordinate frame for a face, and estimate the out-of-plane rotation of a face.

UR - http://www.scopus.com/inward/record.url?scp=0035680902&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035680902&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0035680902

VL - 2

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

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

SN - 1063-6919

ER -