Presentation 2000/12/14
Human-Face Recognition Using Multi-Layer Neural Networks and Orthogonal Transformation
Masahiro YOSHIDA, Hideki ASAI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this research, we try to recognize face images for many persons by multi-layer neural network and orthogonal transform. First, histogram modification and mosaic processing are done to face images. In addition, orthogonal transform is done on the mosaic image. Finally, we try to recognize the face image by using NN, where a part of data, which is orthogonal transform of the mosaic image, is used. We have used two types of techniques of 2-dimensional discrete Fourier transform and 2-dimentional descrete Walsh transform for orthogonal transform. We estimate the recognition rate for each of two types of orthogonal transforms.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) face image recognition / multi-layer neural network / orthogonal transform / 2-dimensional discrete Fourier transform / 2-dimensional discrete Walsh transform
Paper # NLP2000-118
Date of Issue

Conference Information
Committee NLP
Conference Date 2000/12/14(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 Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Human-Face Recognition Using Multi-Layer Neural Networks and Orthogonal Transformation
Sub Title (in English)
Keyword(1) face image recognition
Keyword(2) multi-layer neural network
Keyword(3) orthogonal transform
Keyword(4) 2-dimensional discrete Fourier transform
Keyword(5) 2-dimensional discrete Walsh transform
1st Author's Name Masahiro YOSHIDA
1st Author's Affiliation Department of Systems Engineering, Shizuoka University()
2nd Author's Name Hideki ASAI
2nd Author's Affiliation Department of Systems Engineering, Shizuoka University
Date 2000/12/14
Paper # NLP2000-118
Volume (vol) vol.100
Number (no) 518
Page pp.pp.-
#Pages 6
Date of Issue