Combining Illumination Normalization Methods for Better Face Recognition

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)

Abstract

Face Recognition under uncontrolled illumination conditions is partly an unsolved problem. There are two categories of illumination normalization methods. The first category performs a local preprocessing, where they correct a pixel value based on a local neighborhood in the images. The second category performs a global preprocessing step, where the illumination conditions and the face shape of the entire image are estimated. We use two illumination normalization methods from both categories, namely Local Binary Patterns and Model-based Face Illumination Correction. The preprocessed face images of both methods are individually classified with a face recognition algorithm which gives us two similarity scores for a face image. We combine the similarity scores using score-level fusion, decision-level fusion and hybrid fusion. In our previous work, we show that combining the similarity score of different methods using fusion can improve the performance of biometric systems. We achieved a significant performance improvement in comparison with the individual methods.
Original languageEnglish
Title of host publicationAdvances in biometrics
Subtitle of host publicationThird International Conference, ICB 2009, Alghero, Italy, June 2-5, 2009. Proceedings
EditorsMassimo Tistarelli, Mark S. Nixon
Place of PublicationBerlin
PublisherSpringer
Pages404-413
Number of pages10
ISBN (Print)978-3-642-01792-6
DOIs
Publication statusPublished - 4 Jun 2009
Event3rd IAPR International Conference on Biometrics, ICB 2009 - University of Sassari, Alghero, Italy
Duration: 2 Jun 20095 Jun 2009
Conference number: 3

Publication series

NameLecture Notes in Computer Science
PublisherSpringer Verlag
Volume5558
ISSN (Print)0302-9743

Conference

Conference3rd IAPR International Conference on Biometrics, ICB 2009
Abbreviated titleICB
CountryItaly
CityAlghero
Period2/06/095/06/09

Fingerprint

Face recognition
Lighting
Fusion reactions
Biometrics
Pixels

Keywords

  • METIS-263914
  • Face Recognition
  • Illumination Normalization
  • Decision level fusion
  • Model-based Face Illumination Correction
  • EWI-15683
  • hybrid fusion
  • Score-level fusion
  • Local Binary Patterns
  • SCS-Safety
  • IR-67800

Cite this

Boom, B. J., Tao, Q., Spreeuwers, L. J., & Veldhuis, R. N. J. (2009). Combining Illumination Normalization Methods for Better Face Recognition. In M. Tistarelli, & M. S. Nixon (Eds.), Advances in biometrics: Third International Conference, ICB 2009, Alghero, Italy, June 2-5, 2009. Proceedings (pp. 404-413). (Lecture Notes in Computer Science; Vol. 5558). Berlin: Springer. https://doi.org/10.1007/978-3-642-01793-3_42
Boom, B.J. ; Tao, Q. ; Spreeuwers, Lieuwe Jan ; Veldhuis, Raymond N.J. / Combining Illumination Normalization Methods for Better Face Recognition. Advances in biometrics: Third International Conference, ICB 2009, Alghero, Italy, June 2-5, 2009. Proceedings. editor / Massimo Tistarelli ; Mark S. Nixon. Berlin : Springer, 2009. pp. 404-413 (Lecture Notes in Computer Science).
@inproceedings{f2eaf7a093cc462f9ae2d777a5d599f9,
title = "Combining Illumination Normalization Methods for Better Face Recognition",
abstract = "Face Recognition under uncontrolled illumination conditions is partly an unsolved problem. There are two categories of illumination normalization methods. The first category performs a local preprocessing, where they correct a pixel value based on a local neighborhood in the images. The second category performs a global preprocessing step, where the illumination conditions and the face shape of the entire image are estimated. We use two illumination normalization methods from both categories, namely Local Binary Patterns and Model-based Face Illumination Correction. The preprocessed face images of both methods are individually classified with a face recognition algorithm which gives us two similarity scores for a face image. We combine the similarity scores using score-level fusion, decision-level fusion and hybrid fusion. In our previous work, we show that combining the similarity score of different methods using fusion can improve the performance of biometric systems. We achieved a significant performance improvement in comparison with the individual methods.",
keywords = "METIS-263914, Face Recognition, Illumination Normalization, Decision level fusion, Model-based Face Illumination Correction, EWI-15683, hybrid fusion, Score-level fusion, Local Binary Patterns, SCS-Safety, IR-67800",
author = "B.J. Boom and Q. Tao and Spreeuwers, {Lieuwe Jan} and Veldhuis, {Raymond N.J.}",
note = "10.1007/978-3-642-01793-3_42",
year = "2009",
month = "6",
day = "4",
doi = "10.1007/978-3-642-01793-3_42",
language = "English",
isbn = "978-3-642-01792-6",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "404--413",
editor = "Massimo Tistarelli and Nixon, {Mark S.}",
booktitle = "Advances in biometrics",

}

Boom, BJ, Tao, Q, Spreeuwers, LJ & Veldhuis, RNJ 2009, Combining Illumination Normalization Methods for Better Face Recognition. in M Tistarelli & MS Nixon (eds), Advances in biometrics: Third International Conference, ICB 2009, Alghero, Italy, June 2-5, 2009. Proceedings. Lecture Notes in Computer Science, vol. 5558, Springer, Berlin, pp. 404-413, 3rd IAPR International Conference on Biometrics, ICB 2009, Alghero, Italy, 2/06/09. https://doi.org/10.1007/978-3-642-01793-3_42

Combining Illumination Normalization Methods for Better Face Recognition. / Boom, B.J.; Tao, Q.; Spreeuwers, Lieuwe Jan; Veldhuis, Raymond N.J.

Advances in biometrics: Third International Conference, ICB 2009, Alghero, Italy, June 2-5, 2009. Proceedings. ed. / Massimo Tistarelli; Mark S. Nixon. Berlin : Springer, 2009. p. 404-413 (Lecture Notes in Computer Science; Vol. 5558).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Combining Illumination Normalization Methods for Better Face Recognition

AU - Boom, B.J.

AU - Tao, Q.

AU - Spreeuwers, Lieuwe Jan

AU - Veldhuis, Raymond N.J.

N1 - 10.1007/978-3-642-01793-3_42

PY - 2009/6/4

Y1 - 2009/6/4

N2 - Face Recognition under uncontrolled illumination conditions is partly an unsolved problem. There are two categories of illumination normalization methods. The first category performs a local preprocessing, where they correct a pixel value based on a local neighborhood in the images. The second category performs a global preprocessing step, where the illumination conditions and the face shape of the entire image are estimated. We use two illumination normalization methods from both categories, namely Local Binary Patterns and Model-based Face Illumination Correction. The preprocessed face images of both methods are individually classified with a face recognition algorithm which gives us two similarity scores for a face image. We combine the similarity scores using score-level fusion, decision-level fusion and hybrid fusion. In our previous work, we show that combining the similarity score of different methods using fusion can improve the performance of biometric systems. We achieved a significant performance improvement in comparison with the individual methods.

AB - Face Recognition under uncontrolled illumination conditions is partly an unsolved problem. There are two categories of illumination normalization methods. The first category performs a local preprocessing, where they correct a pixel value based on a local neighborhood in the images. The second category performs a global preprocessing step, where the illumination conditions and the face shape of the entire image are estimated. We use two illumination normalization methods from both categories, namely Local Binary Patterns and Model-based Face Illumination Correction. The preprocessed face images of both methods are individually classified with a face recognition algorithm which gives us two similarity scores for a face image. We combine the similarity scores using score-level fusion, decision-level fusion and hybrid fusion. In our previous work, we show that combining the similarity score of different methods using fusion can improve the performance of biometric systems. We achieved a significant performance improvement in comparison with the individual methods.

KW - METIS-263914

KW - Face Recognition

KW - Illumination Normalization

KW - Decision level fusion

KW - Model-based Face Illumination Correction

KW - EWI-15683

KW - hybrid fusion

KW - Score-level fusion

KW - Local Binary Patterns

KW - SCS-Safety

KW - IR-67800

U2 - 10.1007/978-3-642-01793-3_42

DO - 10.1007/978-3-642-01793-3_42

M3 - Conference contribution

SN - 978-3-642-01792-6

T3 - Lecture Notes in Computer Science

SP - 404

EP - 413

BT - Advances in biometrics

A2 - Tistarelli, Massimo

A2 - Nixon, Mark S.

PB - Springer

CY - Berlin

ER -

Boom BJ, Tao Q, Spreeuwers LJ, Veldhuis RNJ. Combining Illumination Normalization Methods for Better Face Recognition. In Tistarelli M, Nixon MS, editors, Advances in biometrics: Third International Conference, ICB 2009, Alghero, Italy, June 2-5, 2009. Proceedings. Berlin: Springer. 2009. p. 404-413. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-642-01793-3_42