Multi-Resolution Face Recognition: The Behaviors of Local Binary Pattern at Different Frequency Bands

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

9 Downloads (Pure)

Abstract

This paper presents an analysis of the recognition performance of LBP at different frequency bands to exploit their discriminative information. The work presented in this paper is part of an investigation about which aspects of a face contribute to automated face recognition. Multi-resolution analysis, by means of wavelet transform, is commonly used to explore the features of an image. The each step of wavelet transform decomposes an image recursively into four frequency bands: approximation, horizontal, vertical, and diagonal band. The approximation band is a down sampled version of the original image. Whereas, the other bands are detail bands that contain detail information of the image in horizontal, vertical, and diagonal directions. The noise is more dominant in these bands. The information contained in the detail bands is more related to high frequency-components and local structures such as edges. In order to analyze the impact of the various bands, we performed classification experiments on them. For the A-bands, that contain the global information of the facial image, we used PCA/LDA classifiers. For the detail bands, that contain local structures, we used LBP.
Original languageEnglish
Title of host publicationProceedings of the 2019 Symposium on Information Theory and Signal Processing in the Benelux
Subtitle of host publicationMay 28-29 2019, KU Leuven, Technologiecampus Gent, Belgium
EditorsGilles Callebaut, Kevin Verniers, Bert Cox
Place of PublicationLeuven
PublisherWerkgemeenschap voor Informatie- en Communicatietheorie (WIC)
Pages63-70
Number of pages8
ISBN (Print)978-94-918-5703-4
Publication statusPublished - 28 May 2019
Event40th WIC Symposium on Information Theory in the Benelux 2019 - Ghent Technology Campus, Leuven, Belgium
Duration: 28 May 201929 May 2019
Conference number: 40

Conference

Conference40th WIC Symposium on Information Theory in the Benelux 2019
CountryBelgium
CityLeuven
Period28/05/1929/05/19

Fingerprint

Face recognition
Wavelet transforms
Frequency bands
Multiresolution analysis
Experiments

Keywords

  • Multi-resolution analysis
  • Face recognition
  • Wavelet transform
  • Local binary patterns

Cite this

Lestriandoko, N. H., Spreeuwers, L., & Veldhuis, R. (2019). Multi-Resolution Face Recognition: The Behaviors of Local Binary Pattern at Different Frequency Bands. In G. Callebaut, K. Verniers, & B. Cox (Eds.), Proceedings of the 2019 Symposium on Information Theory and Signal Processing in the Benelux: May 28-29 2019, KU Leuven, Technologiecampus Gent, Belgium (pp. 63-70). Leuven: Werkgemeenschap voor Informatie- en Communicatietheorie (WIC).
Lestriandoko, Nova Hadi ; Spreeuwers, Luuk ; Veldhuis, Raymond. / Multi-Resolution Face Recognition : The Behaviors of Local Binary Pattern at Different Frequency Bands. Proceedings of the 2019 Symposium on Information Theory and Signal Processing in the Benelux: May 28-29 2019, KU Leuven, Technologiecampus Gent, Belgium. editor / Gilles Callebaut ; Kevin Verniers ; Bert Cox. Leuven : Werkgemeenschap voor Informatie- en Communicatietheorie (WIC), 2019. pp. 63-70
@inproceedings{a34fc561bafe4fcc8b63f21881aef17e,
title = "Multi-Resolution Face Recognition: The Behaviors of Local Binary Pattern at Different Frequency Bands",
abstract = "This paper presents an analysis of the recognition performance of LBP at different frequency bands to exploit their discriminative information. The work presented in this paper is part of an investigation about which aspects of a face contribute to automated face recognition. Multi-resolution analysis, by means of wavelet transform, is commonly used to explore the features of an image. The each step of wavelet transform decomposes an image recursively into four frequency bands: approximation, horizontal, vertical, and diagonal band. The approximation band is a down sampled version of the original image. Whereas, the other bands are detail bands that contain detail information of the image in horizontal, vertical, and diagonal directions. The noise is more dominant in these bands. The information contained in the detail bands is more related to high frequency-components and local structures such as edges. In order to analyze the impact of the various bands, we performed classification experiments on them. For the A-bands, that contain the global information of the facial image, we used PCA/LDA classifiers. For the detail bands, that contain local structures, we used LBP.",
keywords = "Multi-resolution analysis, Face recognition, Wavelet transform, Local binary patterns",
author = "Lestriandoko, {Nova Hadi} and Luuk Spreeuwers and Raymond Veldhuis",
year = "2019",
month = "5",
day = "28",
language = "English",
isbn = "978-94-918-5703-4",
pages = "63--70",
editor = "Gilles Callebaut and Kevin Verniers and Bert Cox",
booktitle = "Proceedings of the 2019 Symposium on Information Theory and Signal Processing in the Benelux",
publisher = "Werkgemeenschap voor Informatie- en Communicatietheorie (WIC)",
address = "Netherlands",

}

Lestriandoko, NH, Spreeuwers, L & Veldhuis, R 2019, Multi-Resolution Face Recognition: The Behaviors of Local Binary Pattern at Different Frequency Bands. in G Callebaut, K Verniers & B Cox (eds), Proceedings of the 2019 Symposium on Information Theory and Signal Processing in the Benelux: May 28-29 2019, KU Leuven, Technologiecampus Gent, Belgium. Werkgemeenschap voor Informatie- en Communicatietheorie (WIC), Leuven, pp. 63-70, 40th WIC Symposium on Information Theory in the Benelux 2019, Leuven, Belgium, 28/05/19.

Multi-Resolution Face Recognition : The Behaviors of Local Binary Pattern at Different Frequency Bands. / Lestriandoko, Nova Hadi ; Spreeuwers, Luuk; Veldhuis, Raymond.

Proceedings of the 2019 Symposium on Information Theory and Signal Processing in the Benelux: May 28-29 2019, KU Leuven, Technologiecampus Gent, Belgium. ed. / Gilles Callebaut; Kevin Verniers; Bert Cox. Leuven : Werkgemeenschap voor Informatie- en Communicatietheorie (WIC), 2019. p. 63-70.

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

TY - GEN

T1 - Multi-Resolution Face Recognition

T2 - The Behaviors of Local Binary Pattern at Different Frequency Bands

AU - Lestriandoko, Nova Hadi

AU - Spreeuwers, Luuk

AU - Veldhuis, Raymond

PY - 2019/5/28

Y1 - 2019/5/28

N2 - This paper presents an analysis of the recognition performance of LBP at different frequency bands to exploit their discriminative information. The work presented in this paper is part of an investigation about which aspects of a face contribute to automated face recognition. Multi-resolution analysis, by means of wavelet transform, is commonly used to explore the features of an image. The each step of wavelet transform decomposes an image recursively into four frequency bands: approximation, horizontal, vertical, and diagonal band. The approximation band is a down sampled version of the original image. Whereas, the other bands are detail bands that contain detail information of the image in horizontal, vertical, and diagonal directions. The noise is more dominant in these bands. The information contained in the detail bands is more related to high frequency-components and local structures such as edges. In order to analyze the impact of the various bands, we performed classification experiments on them. For the A-bands, that contain the global information of the facial image, we used PCA/LDA classifiers. For the detail bands, that contain local structures, we used LBP.

AB - This paper presents an analysis of the recognition performance of LBP at different frequency bands to exploit their discriminative information. The work presented in this paper is part of an investigation about which aspects of a face contribute to automated face recognition. Multi-resolution analysis, by means of wavelet transform, is commonly used to explore the features of an image. The each step of wavelet transform decomposes an image recursively into four frequency bands: approximation, horizontal, vertical, and diagonal band. The approximation band is a down sampled version of the original image. Whereas, the other bands are detail bands that contain detail information of the image in horizontal, vertical, and diagonal directions. The noise is more dominant in these bands. The information contained in the detail bands is more related to high frequency-components and local structures such as edges. In order to analyze the impact of the various bands, we performed classification experiments on them. For the A-bands, that contain the global information of the facial image, we used PCA/LDA classifiers. For the detail bands, that contain local structures, we used LBP.

KW - Multi-resolution analysis

KW - Face recognition

KW - Wavelet transform

KW - Local binary patterns

M3 - Conference contribution

SN - 978-94-918-5703-4

SP - 63

EP - 70

BT - Proceedings of the 2019 Symposium on Information Theory and Signal Processing in the Benelux

A2 - Callebaut, Gilles

A2 - Verniers, Kevin

A2 - Cox, Bert

PB - Werkgemeenschap voor Informatie- en Communicatietheorie (WIC)

CY - Leuven

ER -

Lestriandoko NH, Spreeuwers L, Veldhuis R. Multi-Resolution Face Recognition: The Behaviors of Local Binary Pattern at Different Frequency Bands. In Callebaut G, Verniers K, Cox B, editors, Proceedings of the 2019 Symposium on Information Theory and Signal Processing in the Benelux: May 28-29 2019, KU Leuven, Technologiecampus Gent, Belgium. Leuven: Werkgemeenschap voor Informatie- en Communicatietheorie (WIC). 2019. p. 63-70