Growing Neural Gas (GNG): A Soft Competitive Learning Method for 2<I>D</I> Hand Modelling

Jose GARCIA RODRIGUEZ; Anastassia ANGELOPOULOU; Alexandra PSARROU

doi:10.1093/ietisy/e89-d.7.2124

Growing Neural Gas (GNG): A Soft Competitive Learning Method for 2D Hand Modelling

Jose GARCIA RODRIGUEZ, Anastassia ANGELOPOULOU, Alexandra PSARROU

Full Text Views

0

Cite this

Summary :

A new method for automatically building statistical shape models from a set of training examples and in particular from a class of hands. In this study, we utilise a novel approach to automatically recover the shape of hand outlines from a series of 2D training images. Automated landmark extraction is accomplished through the use of the self-organising model the growing neural gas (GNG) network, which is able to learn and preserve the topological relations of a given set of input patterns without requiring a priori knowledge of the structure of the input space. The GNG is compared to other self-organising networks such as Kohonen and Neural Gas (NG) maps and results are given for the training set of hand outlines, showing that the proposed method preserves accurate models.

Publication: IEICE TRANSACTIONS on Information Vol.E89-D No.7 pp.2124-2131

Publication Date: 2006/07/01

Publicized

Online ISSN: 1745-1361

DOI: 10.1093/ietisy/e89-d.7.2124

Type of Manuscript: Special Section PAPER (Special Section on Machine Vision Applications)

Category: Shape Models

Cite this

Copy

Jose GARCIA RODRIGUEZ, Anastassia ANGELOPOULOU, Alexandra PSARROU, "Growing Neural Gas (GNG): A Soft Competitive Learning Method for 2D Hand Modelling" in IEICE TRANSACTIONS on Information, vol. E89-D, no. 7, pp. 2124-2131, July 2006, doi: 10.1093/ietisy/e89-d.7.2124.
Abstract: A new method for automatically building statistical shape models from a set of training examples and in particular from a class of hands. In this study, we utilise a novel approach to automatically recover the shape of hand outlines from a series of 2D training images. Automated landmark extraction is accomplished through the use of the self-organising model the growing neural gas (GNG) network, which is able to learn and preserve the topological relations of a given set of input patterns without requiring a priori knowledge of the structure of the input space. The GNG is compared to other self-organising networks such as Kohonen and Neural Gas (NG) maps and results are given for the training set of hand outlines, showing that the proposed method preserves accurate models.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.7.2124/_p

Copy

@ARTICLE{e89-d_7_2124,
author={Jose GARCIA RODRIGUEZ, Anastassia ANGELOPOULOU, Alexandra PSARROU, },
journal={IEICE TRANSACTIONS on Information},
title={Growing Neural Gas (GNG): A Soft Competitive Learning Method for 2D Hand Modelling},
year={2006},
volume={E89-D},
number={7},
pages={2124-2131},
abstract={A new method for automatically building statistical shape models from a set of training examples and in particular from a class of hands. In this study, we utilise a novel approach to automatically recover the shape of hand outlines from a series of 2D training images. Automated landmark extraction is accomplished through the use of the self-organising model the growing neural gas (GNG) network, which is able to learn and preserve the topological relations of a given set of input patterns without requiring a priori knowledge of the structure of the input space. The GNG is compared to other self-organising networks such as Kohonen and Neural Gas (NG) maps and results are given for the training set of hand outlines, showing that the proposed method preserves accurate models.},
keywords={},
doi={10.1093/ietisy/e89-d.7.2124},
ISSN={1745-1361},
month={July},}

Copy

TY - JOUR
TI - Growing Neural Gas (GNG): A Soft Competitive Learning Method for 2D Hand Modelling
T2 - IEICE TRANSACTIONS on Information
SP - 2124
EP - 2131
AU - Jose GARCIA RODRIGUEZ
AU - Anastassia ANGELOPOULOU
AU - Alexandra PSARROU
PY - 2006
DO - 10.1093/ietisy/e89-d.7.2124
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2006
AB - A new method for automatically building statistical shape models from a set of training examples and in particular from a class of hands. In this study, we utilise a novel approach to automatically recover the shape of hand outlines from a series of 2D training images. Automated landmark extraction is accomplished through the use of the self-organising model the growing neural gas (GNG) network, which is able to learn and preserve the topological relations of a given set of input patterns without requiring a priori knowledge of the structure of the input space. The GNG is compared to other self-organising networks such as Kohonen and Neural Gas (NG) maps and results are given for the training set of hand outlines, showing that the proposed method preserves accurate models.
ER -