CFART: a multi-resolutional adaptive resonance system

Author

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

Author_Institution

Dept. of Electr. Eng. & Comput. Sci., Northwestern Univ., Evanston, IL, USA

Volume

2

fYear

1996

fDate

3-6 Jun 1996

Firstpage

1312

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 search 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, providing a multi-resolutional representation of 3D objects. In the experiments, we use superquadrics as a demonstration example

Keywords

ART neural nets; computer vision; dynamics; fuzzy neural nets; object recognition; search problems; stereo image processing; unsupervised learning; visual databases; 3D object recognition; bottom-up learning process; cascade fuzzy ART network; categorization; fuzzy neural network; hierarchical representation; multiresolutional adaptive resonance system; self-organization; top-down search; unsupervised learning; Adaptive systems; Computer science; Databases; Information science; Neural networks; Object recognition; Power system modeling; Resonance; Subspace constraints; Unsupervised learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 1996., IEEE International Conference on

Conference_Location

Washington, DC

Print_ISBN

0-7803-3210-5

Type

conf

DOI

10.1109/ICNN.1996.549088

Filename

549088