Presentation 2003/9/2
Recover of the multiple shapes by segmentation from sequences of scaled orthographic images via autoassociative learning
Jun FUJIKI, Takashi TAKAHASHI, Takio KURITA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Segmentation of multiple objects in images is the fundamental problem in computer vison and many methods arc presented. All the methods depends on the separation of the column space of shape matrix into the direct sum of linear subspaces. In this paper, we segment multi objects by using multiple three-layered perceptron. We evaluate the ability of the algorithm through experiment with synthesize data.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) structure from motion / scaled orthographic projection / Euclidean reconstruction / multi objects / autoassociative learning
Paper # PRMU2003-110
Date of Issue

Conference Information
Committee PRMU
Conference Date 2003/9/2(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Recover of the multiple shapes by segmentation from sequences of scaled orthographic images via autoassociative learning
Sub Title (in English)
Keyword(1) structure from motion
Keyword(2) scaled orthographic projection
Keyword(3) Euclidean reconstruction
Keyword(4) multi objects
Keyword(5) autoassociative learning
1st Author's Name Jun FUJIKI
1st Author's Affiliation National Institute of Advanced Industrial Science and Technology()
2nd Author's Name Takashi TAKAHASHI
2nd Author's Affiliation Faculty of Science and Technology, Ryukoku University
3rd Author's Name Takio KURITA
3rd Author's Affiliation National Institute of Advanced Industrial Science and Technology
Date 2003/9/2
Paper # PRMU2003-110
Volume (vol) vol.103
Number (no) 296
Page pp.pp.-
#Pages 4
Date of Issue