Weighted module image method for face recognition

Yingling Feng; Hongyu Wang; Caikou Chen; Changbo Wang

Weighted module image method for face recognition

Yingling Feng^*
, Hongyu Wang
, Caikou Chen
, Changbo Wang

^*Corresponding author for this work

School of Data Science and Engineering

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

In this paper, we use the distances between the images and the average image of the within class as the weights to generate new samples. Such samples are closer to the real face than the original ones. Then merged with the module image method, we divide the weighted images to extract the feature with PCA. This method can reduce the effects of the lighting and poses before the camera, and can extract the local information of the image. It is proved having higher recognition than the Module PCA through experiments.

Original language	English
Pages (from-to)	1-4
Number of pages	4
Journal	Journal of Soochow University Engineering Science Edition
Volume	30
Issue number	6
State	Published - Dec 2010

Keywords

Distance
Feature extraction
Module image
Weight

Cite this

@article{a78806672e5d4e0a83903a3e779e4f43,

title = "Weighted module image method for face recognition",

abstract = "In this paper, we use the distances between the images and the average image of the within class as the weights to generate new samples. Such samples are closer to the real face than the original ones. Then merged with the module image method, we divide the weighted images to extract the feature with PCA. This method can reduce the effects of the lighting and poses before the camera, and can extract the local information of the image. It is proved having higher recognition than the Module PCA through experiments.",

keywords = "Distance, Feature extraction, Module image, Weight",

author = "Yingling Feng and Hongyu Wang and Caikou Chen and Changbo Wang",

year = "2010",

month = dec,

language = "英语",

volume = "30",

pages = "1--4",

journal = "Journal of Soochow University Engineering Science Edition",

issn = "1673-047X",

publisher = "Soochow University Press",

number = "6",

}

TY - JOUR

T1 - Weighted module image method for face recognition

AU - Feng, Yingling

AU - Wang, Hongyu

AU - Chen, Caikou

AU - Wang, Changbo

PY - 2010/12

Y1 - 2010/12

N2 - In this paper, we use the distances between the images and the average image of the within class as the weights to generate new samples. Such samples are closer to the real face than the original ones. Then merged with the module image method, we divide the weighted images to extract the feature with PCA. This method can reduce the effects of the lighting and poses before the camera, and can extract the local information of the image. It is proved having higher recognition than the Module PCA through experiments.

AB - In this paper, we use the distances between the images and the average image of the within class as the weights to generate new samples. Such samples are closer to the real face than the original ones. Then merged with the module image method, we divide the weighted images to extract the feature with PCA. This method can reduce the effects of the lighting and poses before the camera, and can extract the local information of the image. It is proved having higher recognition than the Module PCA through experiments.

KW - Distance

KW - Feature extraction

KW - Module image

KW - Weight

UR - https://www.scopus.com/pages/publications/84867241106

M3 - 文章

AN - SCOPUS:84867241106

SN - 1673-047X

VL - 30

SP - 1

EP - 4

JO - Journal of Soochow University Engineering Science Edition

JF - Journal of Soochow University Engineering Science Edition

IS - 6

ER -

Weighted module image method for face recognition

Abstract

Keywords

Other files and links

Fingerprint

Cite this