Presentation 1998/3/20
A Visual Nervous System based Multi-Module Neural Network for Object Recognition
Tetsuya TNNAI, Masafumi HAGIWARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) When we recognize a object, unite the part features, and recognize whole object. We propose a multi-module neural network model based on information processing of the visual nervous system. In this paper, we constract the system that extract a human face area from image with background. This system consists of several modules that is learned to respond selectively to human face component, eyes, nose, and mouth. At last extract face area where the outputs of previous cell layer is located correctly to human face component. We carried out a lot of experiments using 100 images having complex background to examine the effectiveness of the proposed scheme. 83% of faces are detected correctly.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Visual Nervous System / Multi-Module / Neocognitron / Part Feature / Face Extraction
Paper #
Date of Issue

Conference Information
Committee NC
Conference Date 1998/3/20(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 Visual Nervous System based Multi-Module Neural Network for Object Recognition
Sub Title (in English)
Keyword(1) Visual Nervous System
Keyword(2) Multi-Module
Keyword(3) Neocognitron
Keyword(4) Part Feature
Keyword(5) Face Extraction
1st Author's Name Tetsuya TNNAI
1st Author's Affiliation Department of Electrical Engineering, Faculty of Science and Technology, Keio University()
2nd Author's Name Masafumi HAGIWARA
2nd Author's Affiliation Department of Electrical Engineering, Faculty of Science and Technology, Keio University
Date 1998/3/20
Paper #
Volume (vol) vol.97
Number (no) 624
Page pp.pp.-
#Pages 8
Date of Issue