Face Image Recognition by 2-Dimensional Discrete Walsh Transform and Multi-Layer Neural Network

Masahiro YOSHIDA; Takeshi KAMIO; Hideki ASAI

Face Image Recognition by 2-Dimensional Discrete Walsh Transform and Multi-Layer Neural Network

Masahiro YOSHIDA, Takeshi KAMIO, Hideki ASAI

Full Text Views

0

Share
Cite this

Summary :

This report describes face image recognition by 2-dimensional discrete Walsh transform and multi-layer neural networks. Neural network (NN) is one of the powerful tools for pattern recognition. In the previous researches of face image recognition by NN, the gray levels on each pixel of the face image have been used for input data to NN. However, because the face image has usually too many pixels, a variety of approaches have been required to reduce the number of the input data. In this research, 2-dimensional discrete Walsh transform is used for reduction of input data and the recognition is done by multi-layer neural networks. Finally, the validity of our method is varified.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E86-A No.10 pp.2623-2627

Publication Date: 2003/10/01

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section LETTER (Special Section on Information Theory and Its Applications)

Category: Source Coding/Image Processing

Cite this

Copy

Masahiro YOSHIDA, Takeshi KAMIO, Hideki ASAI, "Face Image Recognition by 2-Dimensional Discrete Walsh Transform and Multi-Layer Neural Network" in IEICE TRANSACTIONS on Fundamentals, vol. E86-A, no. 10, pp. 2623-2627, October 2003, doi: .
Abstract: This report describes face image recognition by 2-dimensional discrete Walsh transform and multi-layer neural networks. Neural network (NN) is one of the powerful tools for pattern recognition. In the previous researches of face image recognition by NN, the gray levels on each pixel of the face image have been used for input data to NN. However, because the face image has usually too many pixels, a variety of approaches have been required to reduce the number of the input data. In this research, 2-dimensional discrete Walsh transform is used for reduction of input data and the recognition is done by multi-layer neural networks. Finally, the validity of our method is varified.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/e86-a_10_2623/_p

Copy

@ARTICLE{e86-a_10_2623,
author={Masahiro YOSHIDA, Takeshi KAMIO, Hideki ASAI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Face Image Recognition by 2-Dimensional Discrete Walsh Transform and Multi-Layer Neural Network},
year={2003},
volume={E86-A},
number={10},
pages={2623-2627},
abstract={This report describes face image recognition by 2-dimensional discrete Walsh transform and multi-layer neural networks. Neural network (NN) is one of the powerful tools for pattern recognition. In the previous researches of face image recognition by NN, the gray levels on each pixel of the face image have been used for input data to NN. However, because the face image has usually too many pixels, a variety of approaches have been required to reduce the number of the input data. In this research, 2-dimensional discrete Walsh transform is used for reduction of input data and the recognition is done by multi-layer neural networks. Finally, the validity of our method is varified.},
keywords={},
doi={},
ISSN={},
month={October},}

Copy

TY - JOUR
TI - Face Image Recognition by 2-Dimensional Discrete Walsh Transform and Multi-Layer Neural Network
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2623
EP - 2627
AU - Masahiro YOSHIDA
AU - Takeshi KAMIO
AU - Hideki ASAI
PY - 2003
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E86-A
IS - 10
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - October 2003
AB - This report describes face image recognition by 2-dimensional discrete Walsh transform and multi-layer neural networks. Neural network (NN) is one of the powerful tools for pattern recognition. In the previous researches of face image recognition by NN, the gray levels on each pixel of the face image have been used for input data to NN. However, because the face image has usually too many pixels, a variety of approaches have been required to reduce the number of the input data. In this research, 2-dimensional discrete Walsh transform is used for reduction of input data and the recognition is done by multi-layer neural networks. Finally, the validity of our method is varified.
ER -