Presentation 1996/3/18
Face Image Extraction using the Degree of Dependencein a Neural Network with the Dynamic Link Architecture
Mitsuyoshi IKEDA, Koichiro YAMAUCHI, Naohiro ISHII,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Many face recognizing systems have been proposed. Almost all of them recognize face images without background images. However, the natural face images always include some background images. So, it is difficult to use these systems directly for the natural face image recognition. To solve this problem, we propose a face image extracting system using a Degree or Dependence in a neural network with the Dynamic Link Architecture (DLA). In the first step, the neural network with DLA recognizes a deformed face image including back ground images. Then, the system detects attentive regions of the neural network using the Degree of Dependence in it. In the final step, the system extracts the detected region from the image.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Neural Network / degree of dependence / Dynamic Link Architecture
Paper # NC-95-137
Date of Issue

Conference Information
Committee NC
Conference Date 1996/3/18(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) Face Image Extraction using the Degree of Dependencein a Neural Network with the Dynamic Link Architecture
Sub Title (in English)
Keyword(1) Neural Network
Keyword(2) degree of dependence
Keyword(3) Dynamic Link Architecture
1st Author's Name Mitsuyoshi IKEDA
1st Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology()
2nd Author's Name Koichiro YAMAUCHI
2nd Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology
3rd Author's Name Naohiro ISHII
3rd Author's Affiliation Department of Intelligence and Computer Science, Nagoya Institute of Technology
Date 1996/3/18
Paper # NC-95-137
Volume (vol) vol.95
Number (no) 598
Page pp.pp.-
#Pages 8
Date of Issue