Spectroface: A Fourier-based approach for human face recognition

J. H. Lai; P C Yuen; G. C. Feng

Spectroface: A Fourier-based approach for human face recognition

J. H. Lai, P C Yuen, G. C. Feng

Department of Computer Science

Research output: Chapter in book/report/conference proceeding › Conference proceeding

Abstract

This paper presents a new face recognition method in Fourier domain. The proposed method combines the Fourier transform and the wavelet transform for face recognition. Yale and Olivetti face image databases are selected to evaluate the proposed method. The results show that the proposed method gives higher accuracy than (1) eigenface (PCA) method and (2) template matching in spatial domain. The results also show that face recognition performed in Fourier domain gives better accuracy than that in spatial domain.

Original language	English
Title of host publication	Proceedings of the Second International Conference on Multimodal Interface, ICMI 1999
Publisher	International Conference on Multimodal Interface
Pages	VI 115-120
Number of pages	6
Volume	2
Publication status	Published - Jan 1999
Event	2nd International Conference on Multimodal Interface, ICMI 1999 - , Hong Kong Duration: 5 Jan 1999 → 7 Jan 1999

Conference

Conference	2nd International Conference on Multimodal Interface, ICMI 1999
Country/Territory	Hong Kong
Period	5/01/99 → 7/01/99

User-Defined Keywords

Face recognition
Fourier transform
wavelet transform

Cite this

@inproceedings{39d49d03cfb64e7695043c95b3355e88,

title = "Spectroface: A Fourier-based approach for human face recognition",

abstract = "This paper presents a new face recognition method in Fourier domain. The proposed method combines the Fourier transform and the wavelet transform for face recognition. Yale and Olivetti face image databases are selected to evaluate the proposed method. The results show that the proposed method gives higher accuracy than (1) eigenface (PCA) method and (2) template matching in spatial domain. The results also show that face recognition performed in Fourier domain gives better accuracy than that in spatial domain.",

keywords = "Face recognition, Fourier transform, wavelet transform",

author = "Lai, {J. H.} and Yuen, {P C} and Feng, {G. C.}",

note = "This project was supported by the Faculty Research Grant, Hong Kong Baptist University. The first author is partly supported by Natural Science Foundation of Guangdong (No: 960033).; 2nd International Conference on Multimodal Interface, ICMI 1999 ; Conference date: 05-01-1999 Through 07-01-1999",

year = "1999",

month = jan,

language = "English",

volume = "2",

pages = "VI 115--120",

booktitle = "Proceedings of the Second International Conference on Multimodal Interface, ICMI 1999",

publisher = "International Conference on Multimodal Interface ",

}

TY - GEN

T1 - Spectroface: A Fourier-based approach for human face recognition

AU - Lai, J. H.

AU - Yuen, P C

AU - Feng, G. C.

N1 - This project was supported by the Faculty Research Grant, Hong Kong Baptist University. The first author is partly supported by Natural Science Foundation of Guangdong (No: 960033).

PY - 1999/1

Y1 - 1999/1

N2 - This paper presents a new face recognition method in Fourier domain. The proposed method combines the Fourier transform and the wavelet transform for face recognition. Yale and Olivetti face image databases are selected to evaluate the proposed method. The results show that the proposed method gives higher accuracy than (1) eigenface (PCA) method and (2) template matching in spatial domain. The results also show that face recognition performed in Fourier domain gives better accuracy than that in spatial domain.

AB - This paper presents a new face recognition method in Fourier domain. The proposed method combines the Fourier transform and the wavelet transform for face recognition. Yale and Olivetti face image databases are selected to evaluate the proposed method. The results show that the proposed method gives higher accuracy than (1) eigenface (PCA) method and (2) template matching in spatial domain. The results also show that face recognition performed in Fourier domain gives better accuracy than that in spatial domain.

KW - Face recognition

KW - Fourier transform

KW - wavelet transform

M3 - Conference proceeding

VL - 2

SP - VI 115-120

BT - Proceedings of the Second International Conference on Multimodal Interface, ICMI 1999

PB - International Conference on Multimodal Interface

T2 - 2nd International Conference on Multimodal Interface, ICMI 1999

Y2 - 5 January 1999 through 7 January 1999

ER -

Spectroface: A Fourier-based approach for human face recognition

Abstract

Conference

User-Defined Keywords

Fingerprint

Cite this