SO dynamic deformation for building of 3-D models

Sei-Wang Chen, George C. Stockman, Kuo-En Chang

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

Three-dimensional (3-D) modeling based on an ensemble of multilayer self-organizing (SO) neural networks is described. Our objective for 3-D modeling is to construct a representation of a 3-D object shape from sensed surface points acquired from the object. Current modeling techniques can be classified into two categories: the static and the dynamic approaches, the former grounded in computational geometry, and the latter rooted in the mechanics of elastic materials. In this paper, a neural-based dynamic modeling approach is presented. The method used is proved to converge and experimental results are shown which support its applicability to real problems.

Original languageEnglish
Pages (from-to)374-387
Number of pages14
JournalIEEE Transactions on Neural Networks
Volume7
Issue number2
DOIs
Publication statusPublished - 1996 Dec 1

Fingerprint

3D Modeling
Self-organizing
3D Model
Self-organizing Neural Network
Computational geometry
Multilayer Neural Network
Computational Geometry
Elastic Material
Dynamic Modeling
3D
Mechanics
Multilayers
Ensemble
Neural networks
Converge
Three-dimensional
Experimental Results
Modeling
Object

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Electrical and Electronic Engineering
  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Hardware and Architecture

Cite this

SO dynamic deformation for building of 3-D models. / Chen, Sei-Wang; Stockman, George C.; Chang, Kuo-En.

In: IEEE Transactions on Neural Networks, Vol. 7, No. 2, 01.12.1996, p. 374-387.

Research output: Contribution to journalArticle

@article{4ce761e98d634f6f9fd71ff3805c9706,
title = "SO dynamic deformation for building of 3-D models",
abstract = "Three-dimensional (3-D) modeling based on an ensemble of multilayer self-organizing (SO) neural networks is described. Our objective for 3-D modeling is to construct a representation of a 3-D object shape from sensed surface points acquired from the object. Current modeling techniques can be classified into two categories: the static and the dynamic approaches, the former grounded in computational geometry, and the latter rooted in the mechanics of elastic materials. In this paper, a neural-based dynamic modeling approach is presented. The method used is proved to converge and experimental results are shown which support its applicability to real problems.",
author = "Sei-Wang Chen and Stockman, {George C.} and Kuo-En Chang",
year = "1996",
month = "12",
day = "1",
doi = "10.1109/72.485673",
language = "English",
volume = "7",
pages = "374--387",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "2162-237X",
publisher = "IEEE Computational Intelligence Society",
number = "2",

}

TY - JOUR

T1 - SO dynamic deformation for building of 3-D models

AU - Chen, Sei-Wang

AU - Stockman, George C.

AU - Chang, Kuo-En

PY - 1996/12/1

Y1 - 1996/12/1

N2 - Three-dimensional (3-D) modeling based on an ensemble of multilayer self-organizing (SO) neural networks is described. Our objective for 3-D modeling is to construct a representation of a 3-D object shape from sensed surface points acquired from the object. Current modeling techniques can be classified into two categories: the static and the dynamic approaches, the former grounded in computational geometry, and the latter rooted in the mechanics of elastic materials. In this paper, a neural-based dynamic modeling approach is presented. The method used is proved to converge and experimental results are shown which support its applicability to real problems.

AB - Three-dimensional (3-D) modeling based on an ensemble of multilayer self-organizing (SO) neural networks is described. Our objective for 3-D modeling is to construct a representation of a 3-D object shape from sensed surface points acquired from the object. Current modeling techniques can be classified into two categories: the static and the dynamic approaches, the former grounded in computational geometry, and the latter rooted in the mechanics of elastic materials. In this paper, a neural-based dynamic modeling approach is presented. The method used is proved to converge and experimental results are shown which support its applicability to real problems.

UR - http://www.scopus.com/inward/record.url?scp=0030104469&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030104469&partnerID=8YFLogxK

U2 - 10.1109/72.485673

DO - 10.1109/72.485673

M3 - Article

C2 - 18255591

AN - SCOPUS:0030104469

VL - 7

SP - 374

EP - 387

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 2162-237X

IS - 2

ER -