Application of semantic features in face recognition

Huiyu Zhou*, Yuan Yuan, Abdul H. Sadka

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

We propose a new face recognition strategy, which integrates the extraction of semantic features from faces with tensor subspace analysis. The semantic features consist of the eyes and mouth, plus the region outlined by the centers of the three components. A new objective function is generated to fuse the semantic and tensor models for finding similarity between a face and its counterpart in the database. Furthermore, singular value decomposition is used to solve the eigenvector problem in the tensor subspace analysis and to project the geometrical properties to the face manifold. Experimental results demonstrate that the proposed semantic feature-based face recognition algorithm has favorable performance with more accurate convergence and less computational efforts.

Original languageEnglish
Pages (from-to)3251-3256
Number of pages6
JournalPattern Recognition
Volume41
Issue number10
DOIs
Publication statusPublished - 1 Oct 2008

Fingerprint

Face recognition
Semantics
Tensors
Electric fuses
Singular value decomposition
Eigenvalues and eigenfunctions

Keywords

  • Face recognition
  • Feature extraction
  • Semantic
  • Tensor subspace analysis

Cite this

Zhou, Huiyu ; Yuan, Yuan ; Sadka, Abdul H. / Application of semantic features in face recognition. In: Pattern Recognition. 2008 ; Vol. 41, No. 10. pp. 3251-3256.
@article{496f588bb1b4449193cfb3723ca1d5bf,
title = "Application of semantic features in face recognition",
abstract = "We propose a new face recognition strategy, which integrates the extraction of semantic features from faces with tensor subspace analysis. The semantic features consist of the eyes and mouth, plus the region outlined by the centers of the three components. A new objective function is generated to fuse the semantic and tensor models for finding similarity between a face and its counterpart in the database. Furthermore, singular value decomposition is used to solve the eigenvector problem in the tensor subspace analysis and to project the geometrical properties to the face manifold. Experimental results demonstrate that the proposed semantic feature-based face recognition algorithm has favorable performance with more accurate convergence and less computational efforts.",
keywords = "Face recognition, Feature extraction, Semantic, Tensor subspace analysis",
author = "Huiyu Zhou and Yuan Yuan and Sadka, {Abdul H.}",
year = "2008",
month = "10",
day = "1",
doi = "10.1016/j.patcog.2008.04.008",
language = "English",
volume = "41",
pages = "3251--3256",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier",
number = "10",

}

Application of semantic features in face recognition. / Zhou, Huiyu; Yuan, Yuan; Sadka, Abdul H.

In: Pattern Recognition, Vol. 41, No. 10, 01.10.2008, p. 3251-3256.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Application of semantic features in face recognition

AU - Zhou, Huiyu

AU - Yuan, Yuan

AU - Sadka, Abdul H.

PY - 2008/10/1

Y1 - 2008/10/1

N2 - We propose a new face recognition strategy, which integrates the extraction of semantic features from faces with tensor subspace analysis. The semantic features consist of the eyes and mouth, plus the region outlined by the centers of the three components. A new objective function is generated to fuse the semantic and tensor models for finding similarity between a face and its counterpart in the database. Furthermore, singular value decomposition is used to solve the eigenvector problem in the tensor subspace analysis and to project the geometrical properties to the face manifold. Experimental results demonstrate that the proposed semantic feature-based face recognition algorithm has favorable performance with more accurate convergence and less computational efforts.

AB - We propose a new face recognition strategy, which integrates the extraction of semantic features from faces with tensor subspace analysis. The semantic features consist of the eyes and mouth, plus the region outlined by the centers of the three components. A new objective function is generated to fuse the semantic and tensor models for finding similarity between a face and its counterpart in the database. Furthermore, singular value decomposition is used to solve the eigenvector problem in the tensor subspace analysis and to project the geometrical properties to the face manifold. Experimental results demonstrate that the proposed semantic feature-based face recognition algorithm has favorable performance with more accurate convergence and less computational efforts.

KW - Face recognition

KW - Feature extraction

KW - Semantic

KW - Tensor subspace analysis

UR - http://www.scopus.com/inward/record.url?scp=45549092040&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2008.04.008

DO - 10.1016/j.patcog.2008.04.008

M3 - Article

AN - SCOPUS:45549092040

VL - 41

SP - 3251

EP - 3256

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 10

ER -