CFART: a multi-resolutional adaptive resonance system

Hai Lung Hung; Hong Yuan Mark Liao; Chwen Jye Sze; Shing Jong Lin; Wei Chung Lin; Kuo Chin Fan

CFART: a multi-resolutional adaptive resonance system

Hai Lung Hung, Hong Yuan Mark Liao, Chwen Jye Sze, Shing Jong Lin, Wei Chung Lin, Kuo Chin Fan

Department of Computer Science and Information Engineering

Research output: Contribution to conference › Paper › peer-review

1 Scopus citations

Abstract

In this paper, a cascade fuzzy ART (CFART) network is developed and applied to 3D object recognition. The proposed CFART network contains multiple layers which can express a hierarchical representation of an input pattern. The learning processes of the proposed network are unsupervised and self-organizing, which include a top-down searching process and a bottom-up learning process. The proposed CFART can accept both binary and analog inputs. With fast learning and categorization capabilities, the proposed network is capable of acting as an extensible database and providing a multi-resolutional representation of 3D objects. In the experiments, we use superquadrics as a demonstrating example.

Original language	English
Pages	1312-1317
Number of pages	6
State	Published - 1996
Event	Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) - Washington, DC, USA Duration: 3 Jun 1996 → 6 Jun 1996

Conference

Conference	Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)
City	Washington, DC, USA
Period	3/06/96 → 6/06/96

Cite this

@conference{9aa398659db240bea0db89c2d6605596,

title = "CFART: a multi-resolutional adaptive resonance system",

abstract = "In this paper, a cascade fuzzy ART (CFART) network is developed and applied to 3D object recognition. The proposed CFART network contains multiple layers which can express a hierarchical representation of an input pattern. The learning processes of the proposed network are unsupervised and self-organizing, which include a top-down searching process and a bottom-up learning process. The proposed CFART can accept both binary and analog inputs. With fast learning and categorization capabilities, the proposed network is capable of acting as an extensible database and providing a multi-resolutional representation of 3D objects. In the experiments, we use superquadrics as a demonstrating example.",

author = "Hung, {Hai Lung} and Liao, {Hong Yuan Mark} and Sze, {Chwen Jye} and Lin, {Shing Jong} and Lin, {Wei Chung} and Fan, {Kuo Chin}",

year = "1996",

language = "???core.languages.en_GB???",

pages = "1312--1317",

note = "null ; Conference date: 03-06-1996 Through 06-06-1996",

}

CFART : a multi-resolutional adaptive resonance system. / Hung, Hai Lung; Liao, Hong Yuan Mark; Sze, Chwen Jye; Lin, Shing Jong; Lin, Wei Chung; Fan, Kuo Chin.

1996. 1312-1317 Paper presented at Proceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4), Washington, DC, USA.

Research output: Contribution to conference › Paper › peer-review

TY - CONF

T1 - CFART

AU - Hung, Hai Lung

AU - Liao, Hong Yuan Mark

AU - Sze, Chwen Jye

AU - Lin, Shing Jong

AU - Lin, Wei Chung

AU - Fan, Kuo Chin

PY - 1996

Y1 - 1996

N2 - In this paper, a cascade fuzzy ART (CFART) network is developed and applied to 3D object recognition. The proposed CFART network contains multiple layers which can express a hierarchical representation of an input pattern. The learning processes of the proposed network are unsupervised and self-organizing, which include a top-down searching process and a bottom-up learning process. The proposed CFART can accept both binary and analog inputs. With fast learning and categorization capabilities, the proposed network is capable of acting as an extensible database and providing a multi-resolutional representation of 3D objects. In the experiments, we use superquadrics as a demonstrating example.

AB - In this paper, a cascade fuzzy ART (CFART) network is developed and applied to 3D object recognition. The proposed CFART network contains multiple layers which can express a hierarchical representation of an input pattern. The learning processes of the proposed network are unsupervised and self-organizing, which include a top-down searching process and a bottom-up learning process. The proposed CFART can accept both binary and analog inputs. With fast learning and categorization capabilities, the proposed network is capable of acting as an extensible database and providing a multi-resolutional representation of 3D objects. In the experiments, we use superquadrics as a demonstrating example.

UR - http://www.scopus.com/inward/record.url?scp=0029728319&partnerID=8YFLogxK

M3 - 會議論文

AN - SCOPUS:0029728319

SP - 1312

EP - 1317

Y2 - 3 June 1996 through 6 June 1996

ER -

CFART: a multi-resolutional adaptive resonance system

Abstract

Conference

Fingerprint

Cite this