Face Recognition Using Composite Features Based on Discriminant Analysis

Sang Il Choi, Sung Sin Lee, Sang Tae Choi, Won-Yong Shin

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Extracting holistic features from the whole face and extracting the local features from the sub-image have pros and cons depending on the conditions. In order to effectively utilize the strengths of various types of holistic features and local features while also complementing each weakness, we propose a method to construct a composite feature vector for face recognition based on discriminant analysis. We first extract the holistic features and the local features from the whole face image and various types of local images using the discriminant feature extraction method. Then, we measure the amount of discriminative information in the individual holistic features and local features and construct composite features with only discriminative features for face recognition. The composite features from the proposed method were compared with the holistic features, local features, and others prepared by hybrid methods through face recognition experiments for various types of face image databases. The proposed composite feature vector displayed better performance than the other methods.

Original languageEnglish
Pages (from-to)13663-13670
Number of pages8
JournalIEEE Access
Volume6
DOIs
Publication statusPublished - 2018 Mar 5

Fingerprint

Discriminant analysis
Face recognition
Composite materials
Feature extraction
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

Choi, Sang Il ; Lee, Sung Sin ; Choi, Sang Tae ; Shin, Won-Yong. / Face Recognition Using Composite Features Based on Discriminant Analysis. In: IEEE Access. 2018 ; Vol. 6. pp. 13663-13670.
@article{def081edca104bcf89d6af9d5a9f67e9,
title = "Face Recognition Using Composite Features Based on Discriminant Analysis",
abstract = "Extracting holistic features from the whole face and extracting the local features from the sub-image have pros and cons depending on the conditions. In order to effectively utilize the strengths of various types of holistic features and local features while also complementing each weakness, we propose a method to construct a composite feature vector for face recognition based on discriminant analysis. We first extract the holistic features and the local features from the whole face image and various types of local images using the discriminant feature extraction method. Then, we measure the amount of discriminative information in the individual holistic features and local features and construct composite features with only discriminative features for face recognition. The composite features from the proposed method were compared with the holistic features, local features, and others prepared by hybrid methods through face recognition experiments for various types of face image databases. The proposed composite feature vector displayed better performance than the other methods.",
author = "Choi, {Sang Il} and Lee, {Sung Sin} and Choi, {Sang Tae} and Won-Yong Shin",
year = "2018",
month = "3",
day = "5",
doi = "10.1109/ACCESS.2018.2812725",
language = "English",
volume = "6",
pages = "13663--13670",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Face Recognition Using Composite Features Based on Discriminant Analysis. / Choi, Sang Il; Lee, Sung Sin; Choi, Sang Tae; Shin, Won-Yong.

In: IEEE Access, Vol. 6, 05.03.2018, p. 13663-13670.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Face Recognition Using Composite Features Based on Discriminant Analysis

AU - Choi, Sang Il

AU - Lee, Sung Sin

AU - Choi, Sang Tae

AU - Shin, Won-Yong

PY - 2018/3/5

Y1 - 2018/3/5

N2 - Extracting holistic features from the whole face and extracting the local features from the sub-image have pros and cons depending on the conditions. In order to effectively utilize the strengths of various types of holistic features and local features while also complementing each weakness, we propose a method to construct a composite feature vector for face recognition based on discriminant analysis. We first extract the holistic features and the local features from the whole face image and various types of local images using the discriminant feature extraction method. Then, we measure the amount of discriminative information in the individual holistic features and local features and construct composite features with only discriminative features for face recognition. The composite features from the proposed method were compared with the holistic features, local features, and others prepared by hybrid methods through face recognition experiments for various types of face image databases. The proposed composite feature vector displayed better performance than the other methods.

AB - Extracting holistic features from the whole face and extracting the local features from the sub-image have pros and cons depending on the conditions. In order to effectively utilize the strengths of various types of holistic features and local features while also complementing each weakness, we propose a method to construct a composite feature vector for face recognition based on discriminant analysis. We first extract the holistic features and the local features from the whole face image and various types of local images using the discriminant feature extraction method. Then, we measure the amount of discriminative information in the individual holistic features and local features and construct composite features with only discriminative features for face recognition. The composite features from the proposed method were compared with the holistic features, local features, and others prepared by hybrid methods through face recognition experiments for various types of face image databases. The proposed composite feature vector displayed better performance than the other methods.

UR - http://www.scopus.com/inward/record.url?scp=85043396442&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043396442&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2812725

DO - 10.1109/ACCESS.2018.2812725

M3 - Article

AN - SCOPUS:85043396442

VL - 6

SP - 13663

EP - 13670

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

ER -