3D texture classification using the belief net of a segmentation tree

Sinisa Todorovic, Narendra Ahuja

Research output: Contribution to journalConference article

Abstract

This paper presents a statistical approach to 3D texture classification from a single image obtained under unknown viewpoint and illumination. Unlike in prior work, in which texture primitives (textons) are defined in a filter-response space, and texture classes modeled by frequency histograms of these textons, we seek to extract and model geometric and photometric properties of image regions defining the texture. To this end, texture images are first segmented by a multiscale segmentation algorithm, and a universal set of texture primitives is specified over all texture classes in the domain of region geometric and photometric properties. Then, for each class, a tree-structured belief network (TSBN) is learned, where nodes represent the corresponding image regions, and edges, their statistical dependecies. A given unknown texture is classified with respect to the maximum posterior distribution of the TSBN. Experimental results on the benchmark CUReT database demonstrate that our approach outperforms the state-of-the-art methods.

Original languageEnglish (US)
Article number1699776
Pages (from-to)33-36
Number of pages4
JournalProceedings - International Conference on Pattern Recognition
Volume4
DOIs
StatePublished - Dec 1 2006
Event18th International Conference on Pattern Recognition, ICPR 2006 - Hong Kong, China
Duration: Aug 20 2006Aug 24 2006

Fingerprint

Textures
Bayesian networks
Lighting

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

3D texture classification using the belief net of a segmentation tree. / Todorovic, Sinisa; Ahuja, Narendra.

In: Proceedings - International Conference on Pattern Recognition, Vol. 4, 1699776, 01.12.2006, p. 33-36.

Research output: Contribution to journalConference article

@article{90f39ddf2a724dae8df89d93f34878ec,
title = "3D texture classification using the belief net of a segmentation tree",
abstract = "This paper presents a statistical approach to 3D texture classification from a single image obtained under unknown viewpoint and illumination. Unlike in prior work, in which texture primitives (textons) are defined in a filter-response space, and texture classes modeled by frequency histograms of these textons, we seek to extract and model geometric and photometric properties of image regions defining the texture. To this end, texture images are first segmented by a multiscale segmentation algorithm, and a universal set of texture primitives is specified over all texture classes in the domain of region geometric and photometric properties. Then, for each class, a tree-structured belief network (TSBN) is learned, where nodes represent the corresponding image regions, and edges, their statistical dependecies. A given unknown texture is classified with respect to the maximum posterior distribution of the TSBN. Experimental results on the benchmark CUReT database demonstrate that our approach outperforms the state-of-the-art methods.",
author = "Sinisa Todorovic and Narendra Ahuja",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/ICPR.2006.34",
language = "English (US)",
volume = "4",
pages = "33--36",
journal = "Proceedings - International Conference on Pattern Recognition",
issn = "1051-4651",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - 3D texture classification using the belief net of a segmentation tree

AU - Todorovic, Sinisa

AU - Ahuja, Narendra

PY - 2006/12/1

Y1 - 2006/12/1

N2 - This paper presents a statistical approach to 3D texture classification from a single image obtained under unknown viewpoint and illumination. Unlike in prior work, in which texture primitives (textons) are defined in a filter-response space, and texture classes modeled by frequency histograms of these textons, we seek to extract and model geometric and photometric properties of image regions defining the texture. To this end, texture images are first segmented by a multiscale segmentation algorithm, and a universal set of texture primitives is specified over all texture classes in the domain of region geometric and photometric properties. Then, for each class, a tree-structured belief network (TSBN) is learned, where nodes represent the corresponding image regions, and edges, their statistical dependecies. A given unknown texture is classified with respect to the maximum posterior distribution of the TSBN. Experimental results on the benchmark CUReT database demonstrate that our approach outperforms the state-of-the-art methods.

AB - This paper presents a statistical approach to 3D texture classification from a single image obtained under unknown viewpoint and illumination. Unlike in prior work, in which texture primitives (textons) are defined in a filter-response space, and texture classes modeled by frequency histograms of these textons, we seek to extract and model geometric and photometric properties of image regions defining the texture. To this end, texture images are first segmented by a multiscale segmentation algorithm, and a universal set of texture primitives is specified over all texture classes in the domain of region geometric and photometric properties. Then, for each class, a tree-structured belief network (TSBN) is learned, where nodes represent the corresponding image regions, and edges, their statistical dependecies. A given unknown texture is classified with respect to the maximum posterior distribution of the TSBN. Experimental results on the benchmark CUReT database demonstrate that our approach outperforms the state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=34147118484&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34147118484&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2006.34

DO - 10.1109/ICPR.2006.34

M3 - Conference article

AN - SCOPUS:34147118484

VL - 4

SP - 33

EP - 36

JO - Proceedings - International Conference on Pattern Recognition

JF - Proceedings - International Conference on Pattern Recognition

SN - 1051-4651

M1 - 1699776

ER -