Face recognition with local feature patterns and histogram spatially bonstrained earth mover's distance

Wei Zhou, Alireza Ahrary, Seiichiro Kamata

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

3 Citations (Scopus)

Abstract

In this work, two novel local feature patterns-Modified Local Binary patterns (MLBP) and local Ternary patterns (LIP), are proposed for extract features in the facial image, which use some distinct rule to code the values in a label, respectively. These patterns are more invariant to illuminance and face expression compared to traditional one. After getting the local feature patterns, in order to take alignment of face into account, a novel matching method called Histogram Spatially constrained Earth Mover's Distance(HSEMD) is proposed. In this step, the source image is partitioned into non-overlapping local regions while the destination image is represented as a set of overlapping local regions at different positions. Meanwhile, multi-scale cascade mechanism is studied for extracting more feature patterns and obtaining global information of the face.The performance of the proposed method is assessed in the face recognition problem under different challenges. The experimental results show that the proposed method has higher accuracy than some other classic methods.

Original languageEnglish
Title of host publicationICSIPA09 - 2009 IEEE International Conference on Signal and Image Processing Applications, Conference Proceedings
Pages374-379
Number of pages6
DOIs
Publication statusPublished - 2009
Event2009 IEEE International Conference on Signal and Image Processing Applications, ICSIPA09 - Kuala Lumpur
Duration: 2009 Nov 182009 Nov 19

Other

Other2009 IEEE International Conference on Signal and Image Processing Applications, ICSIPA09
CityKuala Lumpur
Period09/11/1809/11/19

Fingerprint

Face recognition
Labels
Earth (planet)

Keywords

  • Face recognition
  • Feature extraction
  • HSEMD
  • Local Feature Patterns
  • LTP
  • MLBP

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing

Cite this

Zhou, W., Ahrary, A., & Kamata, S. (2009). Face recognition with local feature patterns and histogram spatially bonstrained earth mover's distance. In ICSIPA09 - 2009 IEEE International Conference on Signal and Image Processing Applications, Conference Proceedings (pp. 374-379). [5478680] https://doi.org/10.1109/ICSIPA.2009.5478680

Face recognition with local feature patterns and histogram spatially bonstrained earth mover's distance. / Zhou, Wei; Ahrary, Alireza; Kamata, Seiichiro.

ICSIPA09 - 2009 IEEE International Conference on Signal and Image Processing Applications, Conference Proceedings. 2009. p. 374-379 5478680.

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

Zhou, W, Ahrary, A & Kamata, S 2009, Face recognition with local feature patterns and histogram spatially bonstrained earth mover's distance. in ICSIPA09 - 2009 IEEE International Conference on Signal and Image Processing Applications, Conference Proceedings., 5478680, pp. 374-379, 2009 IEEE International Conference on Signal and Image Processing Applications, ICSIPA09, Kuala Lumpur, 09/11/18. https://doi.org/10.1109/ICSIPA.2009.5478680
Zhou W, Ahrary A, Kamata S. Face recognition with local feature patterns and histogram spatially bonstrained earth mover's distance. In ICSIPA09 - 2009 IEEE International Conference on Signal and Image Processing Applications, Conference Proceedings. 2009. p. 374-379. 5478680 https://doi.org/10.1109/ICSIPA.2009.5478680
Zhou, Wei ; Ahrary, Alireza ; Kamata, Seiichiro. / Face recognition with local feature patterns and histogram spatially bonstrained earth mover's distance. ICSIPA09 - 2009 IEEE International Conference on Signal and Image Processing Applications, Conference Proceedings. 2009. pp. 374-379
@inproceedings{2f23191a98ec41bab047a10565000f85,
title = "Face recognition with local feature patterns and histogram spatially bonstrained earth mover's distance",
abstract = "In this work, two novel local feature patterns-Modified Local Binary patterns (MLBP) and local Ternary patterns (LIP), are proposed for extract features in the facial image, which use some distinct rule to code the values in a label, respectively. These patterns are more invariant to illuminance and face expression compared to traditional one. After getting the local feature patterns, in order to take alignment of face into account, a novel matching method called Histogram Spatially constrained Earth Mover's Distance(HSEMD) is proposed. In this step, the source image is partitioned into non-overlapping local regions while the destination image is represented as a set of overlapping local regions at different positions. Meanwhile, multi-scale cascade mechanism is studied for extracting more feature patterns and obtaining global information of the face.The performance of the proposed method is assessed in the face recognition problem under different challenges. The experimental results show that the proposed method has higher accuracy than some other classic methods.",
keywords = "Face recognition, Feature extraction, HSEMD, Local Feature Patterns, LTP, MLBP",
author = "Wei Zhou and Alireza Ahrary and Seiichiro Kamata",
year = "2009",
doi = "10.1109/ICSIPA.2009.5478680",
language = "English",
isbn = "9781424455614",
pages = "374--379",
booktitle = "ICSIPA09 - 2009 IEEE International Conference on Signal and Image Processing Applications, Conference Proceedings",

}

TY - GEN

T1 - Face recognition with local feature patterns and histogram spatially bonstrained earth mover's distance

AU - Zhou, Wei

AU - Ahrary, Alireza

AU - Kamata, Seiichiro

PY - 2009

Y1 - 2009

N2 - In this work, two novel local feature patterns-Modified Local Binary patterns (MLBP) and local Ternary patterns (LIP), are proposed for extract features in the facial image, which use some distinct rule to code the values in a label, respectively. These patterns are more invariant to illuminance and face expression compared to traditional one. After getting the local feature patterns, in order to take alignment of face into account, a novel matching method called Histogram Spatially constrained Earth Mover's Distance(HSEMD) is proposed. In this step, the source image is partitioned into non-overlapping local regions while the destination image is represented as a set of overlapping local regions at different positions. Meanwhile, multi-scale cascade mechanism is studied for extracting more feature patterns and obtaining global information of the face.The performance of the proposed method is assessed in the face recognition problem under different challenges. The experimental results show that the proposed method has higher accuracy than some other classic methods.

AB - In this work, two novel local feature patterns-Modified Local Binary patterns (MLBP) and local Ternary patterns (LIP), are proposed for extract features in the facial image, which use some distinct rule to code the values in a label, respectively. These patterns are more invariant to illuminance and face expression compared to traditional one. After getting the local feature patterns, in order to take alignment of face into account, a novel matching method called Histogram Spatially constrained Earth Mover's Distance(HSEMD) is proposed. In this step, the source image is partitioned into non-overlapping local regions while the destination image is represented as a set of overlapping local regions at different positions. Meanwhile, multi-scale cascade mechanism is studied for extracting more feature patterns and obtaining global information of the face.The performance of the proposed method is assessed in the face recognition problem under different challenges. The experimental results show that the proposed method has higher accuracy than some other classic methods.

KW - Face recognition

KW - Feature extraction

KW - HSEMD

KW - Local Feature Patterns

KW - LTP

KW - MLBP

UR - http://www.scopus.com/inward/record.url?scp=77954480418&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954480418&partnerID=8YFLogxK

U2 - 10.1109/ICSIPA.2009.5478680

DO - 10.1109/ICSIPA.2009.5478680

M3 - Conference contribution

SN - 9781424455614

SP - 374

EP - 379

BT - ICSIPA09 - 2009 IEEE International Conference on Signal and Image Processing Applications, Conference Proceedings

ER -