MetaMorphs

Deformable shape and texture models

Sharon Xiaolei Huang, Dimitris Metaxas, Ting Chen

Research output: Contribution to journalConference article

70 Citations (Scopus)

Abstract

We present a new class of deformable models, MetaMorphs, that consist of both shape and interior texture. The model deformations are derived from both boundary and region information in a common variational framework. This framework represents a generalization of previous model-based segmentation approaches. The shapes of the new models are represented implicitly as "images" in the higher dimensional space of distance transforms. The interior textures are captured using a nonparametric kernel-based approximation of the intensity probability density functions (p.d.f.s) inside the models. The deformations that Meta-Morph models can undergo are defined using a space warping technique - the cubic B-spline based Free Form. Deformations (FFD). When using the models for boundary finding in images, we derive the model dynamics from an energy functional consisting of both edge energy terms and intensity/texture energy terms. This way, the models deform under the influence of forces derived from both boundary and regional information. The proposed MetaMorph deformable models are efficient in convergence, have large attraction range, and are robust to image noise and inhomogeities. Various examples on finding object boundaries in noisy images with complex textures demonstrate the potential of the proposed technique.

Original languageEnglish (US)
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume1
StatePublished - Oct 19 2004
EventProceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2004 - Washington, DC, United States
Duration: Jun 27 2004Jul 2 2004

Fingerprint

Textures
Splines
Probability density function
Dynamic models

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Cite this

@article{5182605303bf424796515dfb768177b9,
title = "MetaMorphs: Deformable shape and texture models",
abstract = "We present a new class of deformable models, MetaMorphs, that consist of both shape and interior texture. The model deformations are derived from both boundary and region information in a common variational framework. This framework represents a generalization of previous model-based segmentation approaches. The shapes of the new models are represented implicitly as {"}images{"} in the higher dimensional space of distance transforms. The interior textures are captured using a nonparametric kernel-based approximation of the intensity probability density functions (p.d.f.s) inside the models. The deformations that Meta-Morph models can undergo are defined using a space warping technique - the cubic B-spline based Free Form. Deformations (FFD). When using the models for boundary finding in images, we derive the model dynamics from an energy functional consisting of both edge energy terms and intensity/texture energy terms. This way, the models deform under the influence of forces derived from both boundary and regional information. The proposed MetaMorph deformable models are efficient in convergence, have large attraction range, and are robust to image noise and inhomogeities. Various examples on finding object boundaries in noisy images with complex textures demonstrate the potential of the proposed technique.",
author = "Huang, {Sharon Xiaolei} and Dimitris Metaxas and Ting Chen",
year = "2004",
month = "10",
day = "19",
language = "English (US)",
volume = "1",
journal = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
issn = "1063-6919",
publisher = "IEEE Computer Society",

}

MetaMorphs : Deformable shape and texture models. / Huang, Sharon Xiaolei; Metaxas, Dimitris; Chen, Ting.

In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 1, 19.10.2004.

Research output: Contribution to journalConference article

TY - JOUR

T1 - MetaMorphs

T2 - Deformable shape and texture models

AU - Huang, Sharon Xiaolei

AU - Metaxas, Dimitris

AU - Chen, Ting

PY - 2004/10/19

Y1 - 2004/10/19

N2 - We present a new class of deformable models, MetaMorphs, that consist of both shape and interior texture. The model deformations are derived from both boundary and region information in a common variational framework. This framework represents a generalization of previous model-based segmentation approaches. The shapes of the new models are represented implicitly as "images" in the higher dimensional space of distance transforms. The interior textures are captured using a nonparametric kernel-based approximation of the intensity probability density functions (p.d.f.s) inside the models. The deformations that Meta-Morph models can undergo are defined using a space warping technique - the cubic B-spline based Free Form. Deformations (FFD). When using the models for boundary finding in images, we derive the model dynamics from an energy functional consisting of both edge energy terms and intensity/texture energy terms. This way, the models deform under the influence of forces derived from both boundary and regional information. The proposed MetaMorph deformable models are efficient in convergence, have large attraction range, and are robust to image noise and inhomogeities. Various examples on finding object boundaries in noisy images with complex textures demonstrate the potential of the proposed technique.

AB - We present a new class of deformable models, MetaMorphs, that consist of both shape and interior texture. The model deformations are derived from both boundary and region information in a common variational framework. This framework represents a generalization of previous model-based segmentation approaches. The shapes of the new models are represented implicitly as "images" in the higher dimensional space of distance transforms. The interior textures are captured using a nonparametric kernel-based approximation of the intensity probability density functions (p.d.f.s) inside the models. The deformations that Meta-Morph models can undergo are defined using a space warping technique - the cubic B-spline based Free Form. Deformations (FFD). When using the models for boundary finding in images, we derive the model dynamics from an energy functional consisting of both edge energy terms and intensity/texture energy terms. This way, the models deform under the influence of forces derived from both boundary and regional information. The proposed MetaMorph deformable models are efficient in convergence, have large attraction range, and are robust to image noise and inhomogeities. Various examples on finding object boundaries in noisy images with complex textures demonstrate the potential of the proposed technique.

UR - http://www.scopus.com/inward/record.url?scp=5044240454&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=5044240454&partnerID=8YFLogxK

M3 - Conference article

VL - 1

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 -