Presentation 1999/1/21
Segmentation of occluded objects by hybrid of selective attention and symbol knowledge
Yoshiyuki Mitsumori, Takashi Omori,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Center fields of image understanding are the pattern processing and the symbol processing. Both processing are often studied independently so far. In this paper, we propose a hybrid system for early stage of image understanding where the symbol processing and the pattern processing exist in parallel and complement mutually. There, the common knowledge that is necessary for their interaction is automatically acquired using the image recollection ability of the selective attention model. Local pattern features are converted into symbolic description. We developed an image segmentation system which is able to recover lacked part of given object using the symbolic inference. The system was applied for an occluded image and the usefulness of the hybrid system was shown.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) symbol processing / pattern processing / selective attention model / hybrid system / occluded image
Paper # NC98-76
Date of Issue

Conference Information
Committee NC
Conference Date 1999/1/21(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Vice Chair

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Segmentation of occluded objects by hybrid of selective attention and symbol knowledge
Sub Title (in English)
Keyword(1) symbol processing
Keyword(2) pattern processing
Keyword(3) selective attention model
Keyword(4) hybrid system
Keyword(5) occluded image
1st Author's Name Yoshiyuki Mitsumori
1st Author's Affiliation Bio-Applications & Systems Engineering, Tokyo University of Agriculture and Technology()
2nd Author's Name Takashi Omori
2nd Author's Affiliation Faculty of Technology, Division of Electrical and Electronic Engineering, Tokyo University of Agriculture and Technology
Date 1999/1/21
Paper # NC98-76
Volume (vol) vol.98
Number (no) 526
Page pp.pp.-
#Pages 8
Date of Issue