LBP-ferns-based feature extraction for robust facial recognition

June Young Jung, Seung Wook Kim, Cheol Hwan Yoo, Won Jae Park, Sung-Jea Ko

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Most facial recognition (FR) systems first extract discriminative features from a facial image and then perform classification. This paper proposes a method aimed at representing human facial traits and a low-dimensional feature extraction method using orthogonal linear discriminant analysis (OLDA). The proposed feature relies on a local binary pattern to represent texture information and random ferns to build a structural model. By concatenating its feature vectors, the proposed method achieves a highdimensional descriptor of the input facial image. In general, the feature dimension is highly related to its discriminative ability. However, higher dimensionality is more complex to compute. Thus, dimensionality reduction is essential for practical FR applications. OLDA is employed to reduce the dimension of the extracted features and improve discriminative performance. With a representative FR database, the proposed method demonstrates a higher recognition rate and low computational complexity compared to existing FR methods. In addition, with a facial image database with disguises, the proposed algorithm demonstrates outstanding performance.

Original languageEnglish
Article number7838098
Pages (from-to)446-453
Number of pages8
JournalIEEE Transactions on Consumer Electronics
Volume62
Issue number4
DOIs
Publication statusPublished - 2016 Nov 1

Fingerprint

Discriminant analysis
Feature extraction
Computational complexity
Textures

Keywords

  • Facial recognition
  • feature extraction
  • local binary patterns
  • orthogonal linear discriminant analysis
  • random-ferns

ASJC Scopus subject areas

  • Media Technology
  • Electrical and Electronic Engineering

Cite this

LBP-ferns-based feature extraction for robust facial recognition. / Jung, June Young; Kim, Seung Wook; Yoo, Cheol Hwan; Park, Won Jae; Ko, Sung-Jea.

In: IEEE Transactions on Consumer Electronics, Vol. 62, No. 4, 7838098, 01.11.2016, p. 446-453.

Research output: Contribution to journalArticle

Jung, June Young ; Kim, Seung Wook ; Yoo, Cheol Hwan ; Park, Won Jae ; Ko, Sung-Jea. / LBP-ferns-based feature extraction for robust facial recognition. In: IEEE Transactions on Consumer Electronics. 2016 ; Vol. 62, No. 4. pp. 446-453.
@article{597309bdc5d44b35ac06b46cb69558e8,
title = "LBP-ferns-based feature extraction for robust facial recognition",
abstract = "Most facial recognition (FR) systems first extract discriminative features from a facial image and then perform classification. This paper proposes a method aimed at representing human facial traits and a low-dimensional feature extraction method using orthogonal linear discriminant analysis (OLDA). The proposed feature relies on a local binary pattern to represent texture information and random ferns to build a structural model. By concatenating its feature vectors, the proposed method achieves a highdimensional descriptor of the input facial image. In general, the feature dimension is highly related to its discriminative ability. However, higher dimensionality is more complex to compute. Thus, dimensionality reduction is essential for practical FR applications. OLDA is employed to reduce the dimension of the extracted features and improve discriminative performance. With a representative FR database, the proposed method demonstrates a higher recognition rate and low computational complexity compared to existing FR methods. In addition, with a facial image database with disguises, the proposed algorithm demonstrates outstanding performance.",
keywords = "Facial recognition, feature extraction, local binary patterns, orthogonal linear discriminant analysis, random-ferns",
author = "Jung, {June Young} and Kim, {Seung Wook} and Yoo, {Cheol Hwan} and Park, {Won Jae} and Sung-Jea Ko",
year = "2016",
month = "11",
day = "1",
doi = "10.1109/TCE.2016.7838098",
language = "English",
volume = "62",
pages = "446--453",
journal = "IEEE Transactions on Consumer Electronics",
issn = "0098-3063",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - LBP-ferns-based feature extraction for robust facial recognition

AU - Jung, June Young

AU - Kim, Seung Wook

AU - Yoo, Cheol Hwan

AU - Park, Won Jae

AU - Ko, Sung-Jea

PY - 2016/11/1

Y1 - 2016/11/1

N2 - Most facial recognition (FR) systems first extract discriminative features from a facial image and then perform classification. This paper proposes a method aimed at representing human facial traits and a low-dimensional feature extraction method using orthogonal linear discriminant analysis (OLDA). The proposed feature relies on a local binary pattern to represent texture information and random ferns to build a structural model. By concatenating its feature vectors, the proposed method achieves a highdimensional descriptor of the input facial image. In general, the feature dimension is highly related to its discriminative ability. However, higher dimensionality is more complex to compute. Thus, dimensionality reduction is essential for practical FR applications. OLDA is employed to reduce the dimension of the extracted features and improve discriminative performance. With a representative FR database, the proposed method demonstrates a higher recognition rate and low computational complexity compared to existing FR methods. In addition, with a facial image database with disguises, the proposed algorithm demonstrates outstanding performance.

AB - Most facial recognition (FR) systems first extract discriminative features from a facial image and then perform classification. This paper proposes a method aimed at representing human facial traits and a low-dimensional feature extraction method using orthogonal linear discriminant analysis (OLDA). The proposed feature relies on a local binary pattern to represent texture information and random ferns to build a structural model. By concatenating its feature vectors, the proposed method achieves a highdimensional descriptor of the input facial image. In general, the feature dimension is highly related to its discriminative ability. However, higher dimensionality is more complex to compute. Thus, dimensionality reduction is essential for practical FR applications. OLDA is employed to reduce the dimension of the extracted features and improve discriminative performance. With a representative FR database, the proposed method demonstrates a higher recognition rate and low computational complexity compared to existing FR methods. In addition, with a facial image database with disguises, the proposed algorithm demonstrates outstanding performance.

KW - Facial recognition

KW - feature extraction

KW - local binary patterns

KW - orthogonal linear discriminant analysis

KW - random-ferns

UR - http://www.scopus.com/inward/record.url?scp=85011968150&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011968150&partnerID=8YFLogxK

U2 - 10.1109/TCE.2016.7838098

DO - 10.1109/TCE.2016.7838098

M3 - Article

AN - SCOPUS:85011968150

VL - 62

SP - 446

EP - 453

JO - IEEE Transactions on Consumer Electronics

JF - IEEE Transactions on Consumer Electronics

SN - 0098-3063

IS - 4

M1 - 7838098

ER -