Presentation 1998/10/24
Learning of View-Invariant Pattern Recognizer with Temporal Context
Kohei INOUE, Kiichi URAHAMA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) RBF neural networks have been used for recognition of 3-dimensional objects view-invariantly on the basis of combination of some prototypical two-dimensional views of objects. In this paper, a feedback path is added to RBF nets for utilizing class-membership outputs at the previous time as a prior informarion at the current time. The network is trained unsupervisedly with the input of time-variant view images of some objects for developing view-invariant recognition capability. Robustification of data distribution enables the network to reject outlier data and to extract an object expected from the recognition at previous times.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) object recognition / RBF networks / membership feedback / roubst distribution
Paper # NC98-43
Date of Issue

Conference Information
Committee NC
Conference Date 1998/10/24(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning of View-Invariant Pattern Recognizer with Temporal Context
Sub Title (in English)
Keyword(1) object recognition
Keyword(2) RBF networks
Keyword(3) membership feedback
Keyword(4) roubst distribution
1st Author's Name Kohei INOUE
1st Author's Affiliation Faculty of Visual Communication Design, Kyushu Institute of Design()
2nd Author's Name Kiichi URAHAMA
2nd Author's Affiliation Faculty of Visual Communication Design, Kyushu Institute of Design
Date 1998/10/24
Paper # NC98-43
Volume (vol) vol.98
Number (no) 365
Page pp.pp.-
#Pages 8
Date of Issue