Structural representation and BPTS learning for shape classification

Zhiyong Wang; Zheru Chi; D. Feng

doi:10.1109/ICONIP.2002.1202146

Structural representation and BPTS learning for shape classification

Zhiyong Wang
, Zheru Chi
, D. Feng

The Hong Kong Polytechnic University

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

4 Citations (Scopus)

Abstract

In this paper, a novel shape classification technique based on a hierarchical shape representation and the back-propagation through structure (BPTS) learning algorithm is proposed. In our representation scheme, a shape is hierarchically represented with the segments composing the contour of the shape by using a scale-space filtering method. The BPTS algorithm is then applied to learn to classify shapes with such a tree-structure representation. Simulations on both artificially generated shape patterns and real world gesture patterns show that robust classification results can be achieved by using a small set of features only.

Original language	English
Title of host publication	ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing
Subtitle of host publication	Computational Intelligence for the E-Age
Publisher	IEEE
Pages	134-138
Number of pages	5
Volume	1
ISBN (Electronic)	9789810475246, 9810475241
DOIs	https://doi.org/10.1109/ICONIP.2002.1202146
Publication status	Published - 1 Jan 2002
Event	9th International Conference on Neural Information Processing, ICONIP 2002 - Orchid Country Club, Singapore, Singapore Duration: 18 Nov 2002 → 22 Nov 2002

Conference

Conference	9th International Conference on Neural Information Processing, ICONIP 2002
Country/Territory	Singapore
City	Singapore
Period	18/11/02 → 22/11/02

ASJC Scopus subject areas

Computer Networks and Communications
Information Systems
Signal Processing

More information

10.1109/ICONIP.2002.1202146

Cite this

@inproceedings{dd1bd5cad4714db9bb70aafa6995c2d5,

title = "Structural representation and BPTS learning for shape classification",

abstract = "In this paper, a novel shape classification technique based on a hierarchical shape representation and the back-propagation through structure (BPTS) learning algorithm is proposed. In our representation scheme, a shape is hierarchically represented with the segments composing the contour of the shape by using a scale-space filtering method. The BPTS algorithm is then applied to learn to classify shapes with such a tree-structure representation. Simulations on both artificially generated shape patterns and real world gesture patterns show that robust classification results can be achieved by using a small set of features only.",

author = "Zhiyong Wang and Zheru Chi and D. Feng",

year = "2002",

month = jan,

day = "1",

doi = "10.1109/ICONIP.2002.1202146",

language = "English",

volume = "1",

pages = "134--138",

booktitle = "ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing",

publisher = "IEEE",

address = "United States",

note = "9th International Conference on Neural Information Processing, ICONIP 2002 ; Conference date: 18-11-2002 Through 22-11-2002",

}

Wang, Z, Chi, Z & Feng, D 2002, Structural representation and BPTS learning for shape classification. in ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. vol. 1, 1202146, IEEE, pp. 134-138, 9th International Conference on Neural Information Processing, ICONIP 2002, Singapore, Singapore, 18/11/02. https://doi.org/10.1109/ICONIP.2002.1202146

Structural representation and BPTS learning for shape classification. / Wang, Zhiyong; Chi, Zheru; Feng, D.
ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. Vol. 1 IEEE, 2002. p. 134-138 1202146.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Structural representation and BPTS learning for shape classification

AU - Wang, Zhiyong

AU - Chi, Zheru

AU - Feng, D.

PY - 2002/1/1

Y1 - 2002/1/1

N2 - In this paper, a novel shape classification technique based on a hierarchical shape representation and the back-propagation through structure (BPTS) learning algorithm is proposed. In our representation scheme, a shape is hierarchically represented with the segments composing the contour of the shape by using a scale-space filtering method. The BPTS algorithm is then applied to learn to classify shapes with such a tree-structure representation. Simulations on both artificially generated shape patterns and real world gesture patterns show that robust classification results can be achieved by using a small set of features only.

AB - In this paper, a novel shape classification technique based on a hierarchical shape representation and the back-propagation through structure (BPTS) learning algorithm is proposed. In our representation scheme, a shape is hierarchically represented with the segments composing the contour of the shape by using a scale-space filtering method. The BPTS algorithm is then applied to learn to classify shapes with such a tree-structure representation. Simulations on both artificially generated shape patterns and real world gesture patterns show that robust classification results can be achieved by using a small set of features only.

UR - https://www.scopus.com/pages/publications/84965046327

U2 - 10.1109/ICONIP.2002.1202146

DO - 10.1109/ICONIP.2002.1202146

M3 - Conference article published in proceeding or book

VL - 1

SP - 134

EP - 138

BT - ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing

PB - IEEE

T2 - 9th International Conference on Neural Information Processing, ICONIP 2002

Y2 - 18 November 2002 through 22 November 2002

ER -

Structural representation and BPTS learning for shape classification

Abstract

Conference

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this