Extraction of Illumination-Invariant Features in Face Recognition by Empirical Mode Decomposition

Dan Zhang; Yuan Yan Tang

doi:10.1007/978-3-642-01793-3_11

Extraction of Illumination-Invariant Features in Face Recognition by Empirical Mode Decomposition

Dan Zhang^*, Yuan Yan Tang

^*Corresponding author for this work

Department of Computer Science

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

4 Citations (Scopus)

Abstract

Two Empirical Mode Decomposition (EMD) based face recognition schemes are proposed in this paper to address variant illumination problem. EMD is a data-driven analysis method for nonlinear and non-stationary signals. It decomposes signals into a set of Intrinsic Mode Functions (IMFs) that containing multiscale features. The features are representative and especially efficient in capturing high-frequency information. The advantages of EMD accord well with the requirements of face recognition under variant illuminations. Earlier studies show that only the low-frequency component is sensitive to illumination changes, it indicates that the corresponding high-frequency components are more robust to the illumination changes. Therefore, two face recognition schemes based on the IMFs are generated. One is using the high-frequency IMF _ss directly for classification. The other one is based on the synthesized face images fused by high-frequency IMF_s.The experimental results on the PIE database verify the efficiency of the proposed methods.

Original language	English
Title of host publication	Advances in Biometrics
Subtitle of host publication	Third International Conferences, ICB 2009, Alghero, Italy, June 2-5, 2009, Proceedings
Editors	Massimo Tistarelli, Mark S. Nixon
Publisher	Springer Berlin Heidelberg
Pages	102-111
Number of pages	10
Edition	1st
ISBN (Electronic)	9783642017933
ISBN (Print)	3642017924, 9783642017926
DOIs	https://doi.org/10.1007/978-3-642-01793-3_11
Publication status	Published - 25 May 2009
Event	3rd International Conference on Advances in Biometrics, ICB 2009 - Alghero, Italy Duration: 2 Jun 2009 → 5 Jun 2009

Publication series

Name	Lecture Notes in Computer Science
Volume	5558
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Name	Image Processing, Computer Vision, Pattern Recognition, and Graphics

Name	ICB: International Conference on Biometrics

Conference

Conference	3rd International Conference on Advances in Biometrics, ICB 2009
Country/Territory	Italy
City	Alghero
Period	2/06/09 → 5/06/09

User-Defined Keywords

Empirical mode decomposition
Face recognition

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-642-01793-3_11

Cite this

Zhang, D., & Tang, Y. Y. (2009). Extraction of Illumination-Invariant Features in Face Recognition by Empirical Mode Decomposition. In M. Tistarelli, & M. S. Nixon (Eds.), Advances in Biometrics: Third International Conferences, ICB 2009, Alghero, Italy, June 2-5, 2009, Proceedings (1st ed., pp. 102-111). (Lecture Notes in Computer Science; Vol. 5558), (Image Processing, Computer Vision, Pattern Recognition, and Graphics), (ICB: International Conference on Biometrics). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-01793-3_11

Zhang, Dan ; Tang, Yuan Yan. / Extraction of Illumination-Invariant Features in Face Recognition by Empirical Mode Decomposition. Advances in Biometrics: Third International Conferences, ICB 2009, Alghero, Italy, June 2-5, 2009, Proceedings. editor / Massimo Tistarelli ; Mark S. Nixon. 1st. ed. Springer Berlin Heidelberg, 2009. pp. 102-111 (Lecture Notes in Computer Science). (Image Processing, Computer Vision, Pattern Recognition, and Graphics). (ICB: International Conference on Biometrics).

@inproceedings{3b336f82b4724fa287a878bef1e498f6,

title = "Extraction of Illumination-Invariant Features in Face Recognition by Empirical Mode Decomposition",

abstract = "Two Empirical Mode Decomposition (EMD) based face recognition schemes are proposed in this paper to address variant illumination problem. EMD is a data-driven analysis method for nonlinear and non-stationary signals. It decomposes signals into a set of Intrinsic Mode Functions (IMFs) that containing multiscale features. The features are representative and especially efficient in capturing high-frequency information. The advantages of EMD accord well with the requirements of face recognition under variant illuminations. Earlier studies show that only the low-frequency component is sensitive to illumination changes, it indicates that the corresponding high-frequency components are more robust to the illumination changes. Therefore, two face recognition schemes based on the IMFs are generated. One is using the high-frequency IMF ss directly for classification. The other one is based on the synthesized face images fused by high-frequency IMFs.The experimental results on the PIE database verify the efficiency of the proposed methods.",

keywords = "Empirical mode decomposition, Face recognition",

author = "Dan Zhang and Tang, {Yuan Yan}",

note = "Publisher copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2009 ; 3rd International Conference on Advances in Biometrics, ICB 2009 ; Conference date: 02-06-2009 Through 05-06-2009",

year = "2009",

month = may,

day = "25",

doi = "10.1007/978-3-642-01793-3_11",

language = "English",

isbn = "3642017924",

series = "Lecture Notes in Computer Science",

publisher = "Springer Berlin Heidelberg",

pages = "102--111",

editor = "Massimo Tistarelli and Nixon, {Mark S.}",

booktitle = "Advances in Biometrics",

edition = "1st",

}

Zhang, D & Tang, YY 2009, Extraction of Illumination-Invariant Features in Face Recognition by Empirical Mode Decomposition. in M Tistarelli & MS Nixon (eds), Advances in Biometrics: Third International Conferences, ICB 2009, Alghero, Italy, June 2-5, 2009, Proceedings. 1st edn, Lecture Notes in Computer Science, vol. 5558, Image Processing, Computer Vision, Pattern Recognition, and Graphics, ICB: International Conference on Biometrics, Springer Berlin Heidelberg, pp. 102-111, 3rd International Conference on Advances in Biometrics, ICB 2009, Alghero, Italy, 2/06/09. https://doi.org/10.1007/978-3-642-01793-3_11

Extraction of Illumination-Invariant Features in Face Recognition by Empirical Mode Decomposition. / Zhang, Dan; Tang, Yuan Yan.
Advances in Biometrics: Third International Conferences, ICB 2009, Alghero, Italy, June 2-5, 2009, Proceedings. ed. / Massimo Tistarelli; Mark S. Nixon. 1st. ed. Springer Berlin Heidelberg, 2009. p. 102-111 (Lecture Notes in Computer Science; Vol. 5558), (Image Processing, Computer Vision, Pattern Recognition, and Graphics), (ICB: International Conference on Biometrics).

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

TY - GEN

T1 - Extraction of Illumination-Invariant Features in Face Recognition by Empirical Mode Decomposition

AU - Zhang, Dan

AU - Tang, Yuan Yan

N1 - Publisher copyright: © Springer-Verlag Berlin Heidelberg 2009

PY - 2009/5/25

Y1 - 2009/5/25

N2 - Two Empirical Mode Decomposition (EMD) based face recognition schemes are proposed in this paper to address variant illumination problem. EMD is a data-driven analysis method for nonlinear and non-stationary signals. It decomposes signals into a set of Intrinsic Mode Functions (IMFs) that containing multiscale features. The features are representative and especially efficient in capturing high-frequency information. The advantages of EMD accord well with the requirements of face recognition under variant illuminations. Earlier studies show that only the low-frequency component is sensitive to illumination changes, it indicates that the corresponding high-frequency components are more robust to the illumination changes. Therefore, two face recognition schemes based on the IMFs are generated. One is using the high-frequency IMF ss directly for classification. The other one is based on the synthesized face images fused by high-frequency IMFs.The experimental results on the PIE database verify the efficiency of the proposed methods.

AB - Two Empirical Mode Decomposition (EMD) based face recognition schemes are proposed in this paper to address variant illumination problem. EMD is a data-driven analysis method for nonlinear and non-stationary signals. It decomposes signals into a set of Intrinsic Mode Functions (IMFs) that containing multiscale features. The features are representative and especially efficient in capturing high-frequency information. The advantages of EMD accord well with the requirements of face recognition under variant illuminations. Earlier studies show that only the low-frequency component is sensitive to illumination changes, it indicates that the corresponding high-frequency components are more robust to the illumination changes. Therefore, two face recognition schemes based on the IMFs are generated. One is using the high-frequency IMF ss directly for classification. The other one is based on the synthesized face images fused by high-frequency IMFs.The experimental results on the PIE database verify the efficiency of the proposed methods.

KW - Empirical mode decomposition

KW - Face recognition

UR - http://www.scopus.com/inward/record.url?scp=69949124868&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-01793-3_11

DO - 10.1007/978-3-642-01793-3_11

M3 - Conference proceeding

AN - SCOPUS:69949124868

SN - 3642017924

SN - 9783642017926

T3 - Lecture Notes in Computer Science

SP - 102

EP - 111

BT - Advances in Biometrics

A2 - Tistarelli, Massimo

A2 - Nixon, Mark S.

PB - Springer Berlin Heidelberg

T2 - 3rd International Conference on Advances in Biometrics, ICB 2009

Y2 - 2 June 2009 through 5 June 2009

ER -

Zhang D, Tang YY. Extraction of Illumination-Invariant Features in Face Recognition by Empirical Mode Decomposition. In Tistarelli M, Nixon MS, editors, Advances in Biometrics: Third International Conferences, ICB 2009, Alghero, Italy, June 2-5, 2009, Proceedings. 1st ed. Springer Berlin Heidelberg. 2009. p. 102-111. (Lecture Notes in Computer Science). (Image Processing, Computer Vision, Pattern Recognition, and Graphics). (ICB: International Conference on Biometrics). doi: 10.1007/978-3-642-01793-3_11

Extraction of Illumination-Invariant Features in Face Recognition by Empirical Mode Decomposition

Abstract

Publication series

Conference

User-Defined Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this