Presentation 1996/10/28
Image Segmentation for 3D Object Recognition Based on the Bidirectional Processing
Toshifumi Fujita, Hiroshi Ando,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The difficulty of 3D object recognition lies in the fact that the retinal image varies significantly when the viewpoint changes or the relative position of multiple objects changes. The human brain may achieve 3D object recognition in the complex real scene using multiple functional modules communicating each other. This paper proposes a 3D object recognition model which integrates the image segmentation and the correspondence estimation based on the bidirectional processing. The model can cope with both the view variation and the multiple objects occluding each other in the image. We evaluated the performance of the proposed model through computer experiments using gray-level images of 3D objects.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) 3D object recognition / Bidirectional processing / Segmentation / Alignment
Paper # NC96-46
Date of Issue

Conference Information
Committee NC
Conference Date 1996/10/28(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) Image Segmentation for 3D Object Recognition Based on the Bidirectional Processing
Sub Title (in English)
Keyword(1) 3D object recognition
Keyword(2) Bidirectional processing
Keyword(3) Segmentation
Keyword(4) Alignment
1st Author's Name Toshifumi Fujita
1st Author's Affiliation ATR Human Information Processing Research Laboratories()
2nd Author's Name Hiroshi Ando
2nd Author's Affiliation ATR Human Information Processing Research Laboratories
Date 1996/10/28
Paper # NC96-46
Volume (vol) vol.96
Number (no) 331
Page pp.pp.-
#Pages 8
Date of Issue