Census regression classification for face recognition against different variations

Yang Ting Chou, Xiao Lu, Jar-Ferr Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Face recognition (FR) is an interesting topic in recent pattern recognition investigation. Especially, the accuracy of FR is the foremost concern for practical applications. Linear regression classification (LRC) is one of the most famous and effective methods in the FR area. However, it could perform inaccuracy under variant situations such as few training samples, lighting changes, and partial occlusions. In this paper, we propose a novel classification based on LRC, which is called the Census regression classification (CRC), for improving the recognition performance. There are two contributions in this paper. First, an adaptive confidence factor based on Hamming distance upon the Census correlation is proposed to classify the importance of each pixel from comparing training images and a testing image. Secondly, we join a regularized parameter to control the balance between the bias and the variance of the estimation. In order to substantiate the effectiveness, the AR database is adopted to evaluate the performance. Besides, the well-known face recognition approaches including PCA, LDA, ICA, SVM, SRC, LRC, LDRC, URC, and KLRC are compared with the proposed CRC. In experimental results, it can be separated into two parts. First, we prove that the Census similarity is useful for accuracy improvement under different variations. Moreover, the CRC can perform well under lighting changes and partial occlusions.

Original languageEnglish
Title of host publication2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509019298
DOIs
Publication statusPublished - 2016 Aug 1
Event12th IEEE Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016 - Bordeaux, France
Duration: 2016 Jul 112016 Jul 12

Publication series

Name2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016

Other

Other12th IEEE Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016
CountryFrance
CityBordeaux
Period16-07-1116-07-12

Fingerprint

Face recognition
Linear regression
Lighting
Hamming distance
Independent component analysis
Pattern recognition
Pixels
Testing

All Science Journal Classification (ASJC) codes

  • Media Technology
  • Signal Processing

Cite this

Chou, Y. T., Lu, X., & Yang, J-F. (2016). Census regression classification for face recognition against different variations. In 2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016 [7528179] (2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IVMSPW.2016.7528179
Chou, Yang Ting ; Lu, Xiao ; Yang, Jar-Ferr. / Census regression classification for face recognition against different variations. 2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016. Institute of Electrical and Electronics Engineers Inc., 2016. (2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016).
@inproceedings{b1ae17228136409e984f856a270b41f4,
title = "Census regression classification for face recognition against different variations",
abstract = "Face recognition (FR) is an interesting topic in recent pattern recognition investigation. Especially, the accuracy of FR is the foremost concern for practical applications. Linear regression classification (LRC) is one of the most famous and effective methods in the FR area. However, it could perform inaccuracy under variant situations such as few training samples, lighting changes, and partial occlusions. In this paper, we propose a novel classification based on LRC, which is called the Census regression classification (CRC), for improving the recognition performance. There are two contributions in this paper. First, an adaptive confidence factor based on Hamming distance upon the Census correlation is proposed to classify the importance of each pixel from comparing training images and a testing image. Secondly, we join a regularized parameter to control the balance between the bias and the variance of the estimation. In order to substantiate the effectiveness, the AR database is adopted to evaluate the performance. Besides, the well-known face recognition approaches including PCA, LDA, ICA, SVM, SRC, LRC, LDRC, URC, and KLRC are compared with the proposed CRC. In experimental results, it can be separated into two parts. First, we prove that the Census similarity is useful for accuracy improvement under different variations. Moreover, the CRC can perform well under lighting changes and partial occlusions.",
author = "Chou, {Yang Ting} and Xiao Lu and Jar-Ferr Yang",
year = "2016",
month = "8",
day = "1",
doi = "10.1109/IVMSPW.2016.7528179",
language = "English",
series = "2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016",
address = "United States",

}

Chou, YT, Lu, X & Yang, J-F 2016, Census regression classification for face recognition against different variations. in 2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016., 7528179, 2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016, Institute of Electrical and Electronics Engineers Inc., 12th IEEE Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016, Bordeaux, France, 16-07-11. https://doi.org/10.1109/IVMSPW.2016.7528179

Census regression classification for face recognition against different variations. / Chou, Yang Ting; Lu, Xiao; Yang, Jar-Ferr.

2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016. Institute of Electrical and Electronics Engineers Inc., 2016. 7528179 (2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Census regression classification for face recognition against different variations

AU - Chou, Yang Ting

AU - Lu, Xiao

AU - Yang, Jar-Ferr

PY - 2016/8/1

Y1 - 2016/8/1

N2 - Face recognition (FR) is an interesting topic in recent pattern recognition investigation. Especially, the accuracy of FR is the foremost concern for practical applications. Linear regression classification (LRC) is one of the most famous and effective methods in the FR area. However, it could perform inaccuracy under variant situations such as few training samples, lighting changes, and partial occlusions. In this paper, we propose a novel classification based on LRC, which is called the Census regression classification (CRC), for improving the recognition performance. There are two contributions in this paper. First, an adaptive confidence factor based on Hamming distance upon the Census correlation is proposed to classify the importance of each pixel from comparing training images and a testing image. Secondly, we join a regularized parameter to control the balance between the bias and the variance of the estimation. In order to substantiate the effectiveness, the AR database is adopted to evaluate the performance. Besides, the well-known face recognition approaches including PCA, LDA, ICA, SVM, SRC, LRC, LDRC, URC, and KLRC are compared with the proposed CRC. In experimental results, it can be separated into two parts. First, we prove that the Census similarity is useful for accuracy improvement under different variations. Moreover, the CRC can perform well under lighting changes and partial occlusions.

AB - Face recognition (FR) is an interesting topic in recent pattern recognition investigation. Especially, the accuracy of FR is the foremost concern for practical applications. Linear regression classification (LRC) is one of the most famous and effective methods in the FR area. However, it could perform inaccuracy under variant situations such as few training samples, lighting changes, and partial occlusions. In this paper, we propose a novel classification based on LRC, which is called the Census regression classification (CRC), for improving the recognition performance. There are two contributions in this paper. First, an adaptive confidence factor based on Hamming distance upon the Census correlation is proposed to classify the importance of each pixel from comparing training images and a testing image. Secondly, we join a regularized parameter to control the balance between the bias and the variance of the estimation. In order to substantiate the effectiveness, the AR database is adopted to evaluate the performance. Besides, the well-known face recognition approaches including PCA, LDA, ICA, SVM, SRC, LRC, LDRC, URC, and KLRC are compared with the proposed CRC. In experimental results, it can be separated into two parts. First, we prove that the Census similarity is useful for accuracy improvement under different variations. Moreover, the CRC can perform well under lighting changes and partial occlusions.

UR - http://www.scopus.com/inward/record.url?scp=84991786788&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84991786788&partnerID=8YFLogxK

U2 - 10.1109/IVMSPW.2016.7528179

DO - 10.1109/IVMSPW.2016.7528179

M3 - Conference contribution

T3 - 2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016

BT - 2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Chou YT, Lu X, Yang J-F. Census regression classification for face recognition against different variations. In 2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016. Institute of Electrical and Electronics Engineers Inc. 2016. 7528179. (2016 IEEE 12th Image, Video, and Multidimensional Signal Processing Workshop, IVMSP 2016). https://doi.org/10.1109/IVMSPW.2016.7528179