A deformable model with cellular neural network

This paper presents a new methodology for deformable models by drawing an analogy between cellular neural network (CNN) and elastic deformation. The potential energy stored in an elastic body as a result of a deformation caused by an external force is propagated among mass points by the local connec...

Full description

Bibliographic Details
Main Authors: Zhong, Yongmin, Shirinzadeh, B., Alici, G., Smith, J.
Other Authors: G Baciu
Format: Conference Paper
Published: The Hong Kong Polytechnic University 2005
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/5856
_version_ 1848744912753786880
author Zhong, Yongmin
Shirinzadeh, B.
Alici, G.
Smith, J.
author2 G Baciu
author_facet G Baciu
Zhong, Yongmin
Shirinzadeh, B.
Alici, G.
Smith, J.
author_sort Zhong, Yongmin
building Curtin Institutional Repository
collection Online Access
description This paper presents a new methodology for deformable models by drawing an analogy between cellular neural network (CNN) and elastic deformation. The potential energy stored in an elastic body as a result of a deformation caused by an external force is propagated among mass points by the local connectivity of cells and the CNN dynamics. An improved CNN model is developed for propagating the energy generated by the external force on the object surface. A method is presented to derive the internal forces from the potential energy distribution established by the CNN. The methodology proposed in this paper can not only deal with large-range deformation, but it can also accommodate both isotropic and anisotropic materials by simply modifying capacitors of cells. Examples are presented to demonstrate the efficacy of the proposed methodology.
first_indexed 2025-11-14T06:09:00Z
format Conference Paper
id curtin-20.500.11937-5856
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:09:00Z
publishDate 2005
publisher The Hong Kong Polytechnic University
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-58562022-10-11T07:42:50Z A deformable model with cellular neural network Zhong, Yongmin Shirinzadeh, B. Alici, G. Smith, J. G Baciu M C Lin R W H Lau D Thalmann analogous systems CNN deformable objects deformation This paper presents a new methodology for deformable models by drawing an analogy between cellular neural network (CNN) and elastic deformation. The potential energy stored in an elastic body as a result of a deformation caused by an external force is propagated among mass points by the local connectivity of cells and the CNN dynamics. An improved CNN model is developed for propagating the energy generated by the external force on the object surface. A method is presented to derive the internal forces from the potential energy distribution established by the CNN. The methodology proposed in this paper can not only deal with large-range deformation, but it can also accommodate both isotropic and anisotropic materials by simply modifying capacitors of cells. Examples are presented to demonstrate the efficacy of the proposed methodology. 2005 Conference Paper http://hdl.handle.net/20.500.11937/5856 The Hong Kong Polytechnic University restricted
spellingShingle analogous systems
CNN
deformable objects
deformation
Zhong, Yongmin
Shirinzadeh, B.
Alici, G.
Smith, J.
A deformable model with cellular neural network
title A deformable model with cellular neural network
title_full A deformable model with cellular neural network
title_fullStr A deformable model with cellular neural network
title_full_unstemmed A deformable model with cellular neural network
title_short A deformable model with cellular neural network
title_sort deformable model with cellular neural network
topic analogous systems
CNN
deformable objects
deformation
url http://hdl.handle.net/20.500.11937/5856