Presentation 1998/6/18
A Method for Calculating Posture of an Object in Massively Parallel Vision
Toshiharu MUKAI, Noboru OHNISHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Image processing systems, each consists of massively parallel photodetectors and digital processing elements on a monolithic circuit, are recently being developed by several researchers. Some early-vision-like processing algorithms are installed in the vision systems. However, these algorithms are not sufficient for applications because output of them is pattern information, so that, in order to respond input, some feature values should be extracted from the pattern. In the present paper, we propose a method for extracting feature values in massively parallel vision. The features can be complex one, such as rotation angle of the object. The method is based on the eigenspace method, but modified to be robust.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Massively parallel vision / Eigenspace method / Robustness
Paper # NC98-16,HIP98-7
Date of Issue

Conference Information
Committee NC
Conference Date 1998/6/18(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) A Method for Calculating Posture of an Object in Massively Parallel Vision
Sub Title (in English)
Keyword(1) Massively parallel vision
Keyword(2) Eigenspace method
Keyword(3) Robustness
1st Author's Name Toshiharu MUKAI
1st Author's Affiliation Bio-Mimetic Control Research Center, RIKEN()
2nd Author's Name Noboru OHNISHI
2nd Author's Affiliation Bio-Mimetic Control Research Center, RIKEN:Faculty of Engineering, Nagoya University
Date 1998/6/18
Paper # NC98-16,HIP98-7
Volume (vol) vol.98
Number (no) 128
Page pp.pp.-
#Pages 7
Date of Issue