A novel face recognition system using hybrid neural and dual eigenspaces methods

Dapeng Zhang; Hui Peng; Jie Zhou; Sankar K. Pal

doi:10.1109/TSMCA.2003.808252

A novel face recognition system using hybrid neural and dual eigenspaces methods

Dapeng Zhang, Hui Peng, Jie Zhou, Sankar K. Pal

Research output: Journal article publication › Journal article › Academic research › peer-review

23 Citations (Scopus)

Abstract

In this paper, we present an automated face recognition (AFR) system that contains two components: eye detection and face recognition. Based on invariant radial basis function (IRBF) networks and knowledge rules of facial topology, a hybrid neural method is proposed to localize human eyes and segment the face region from a scene. A dual eigenspaces method (DEM) is then developed to extract algebraic features of the face and perform the recognition task with a two-layer minimum distance classifier. Experimental results illustrate that the proposed system is effective and robust.

Original language	English
Pages (from-to)	787-793
Number of pages	7
Journal	IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans.
Volume	32
Issue number	6
DOIs	https://doi.org/10.1109/TSMCA.2003.808252
Publication status	Published - 1 Nov 2002

Keywords

Dual eigenspaces method
Eyes detection
Face recognition
Hybrid neural method

ASJC Scopus subject areas

Software
Control and Systems Engineering
Human-Computer Interaction
Computer Science Applications
Electrical and Electronic Engineering

More information

10.1109/TSMCA.2003.808252

http://hdl.handle.net/10397/224

Cite this

@article{a7bb0489fc4b42449da09dd51214efbe,

title = "A novel face recognition system using hybrid neural and dual eigenspaces methods",

abstract = "In this paper, we present an automated face recognition (AFR) system that contains two components: eye detection and face recognition. Based on invariant radial basis function (IRBF) networks and knowledge rules of facial topology, a hybrid neural method is proposed to localize human eyes and segment the face region from a scene. A dual eigenspaces method (DEM) is then developed to extract algebraic features of the face and perform the recognition task with a two-layer minimum distance classifier. Experimental results illustrate that the proposed system is effective and robust.",

keywords = "Dual eigenspaces method, Eyes detection, Face recognition, Hybrid neural method",

author = "Dapeng Zhang and Hui Peng and Jie Zhou and Pal, {Sankar K.}",

year = "2002",

month = nov,

day = "1",

doi = "10.1109/TSMCA.2003.808252",

language = "English",

volume = "32",

pages = "787--793",

journal = "IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans.",

issn = "1083-4427",

publisher = "IEEE Advancing Technology for Humanity",

number = "6",

}

TY - JOUR

T1 - A novel face recognition system using hybrid neural and dual eigenspaces methods

AU - Zhang, Dapeng

AU - Peng, Hui

AU - Zhou, Jie

AU - Pal, Sankar K.

PY - 2002/11/1

Y1 - 2002/11/1

N2 - In this paper, we present an automated face recognition (AFR) system that contains two components: eye detection and face recognition. Based on invariant radial basis function (IRBF) networks and knowledge rules of facial topology, a hybrid neural method is proposed to localize human eyes and segment the face region from a scene. A dual eigenspaces method (DEM) is then developed to extract algebraic features of the face and perform the recognition task with a two-layer minimum distance classifier. Experimental results illustrate that the proposed system is effective and robust.

AB - In this paper, we present an automated face recognition (AFR) system that contains two components: eye detection and face recognition. Based on invariant radial basis function (IRBF) networks and knowledge rules of facial topology, a hybrid neural method is proposed to localize human eyes and segment the face region from a scene. A dual eigenspaces method (DEM) is then developed to extract algebraic features of the face and perform the recognition task with a two-layer minimum distance classifier. Experimental results illustrate that the proposed system is effective and robust.

KW - Dual eigenspaces method

KW - Eyes detection

KW - Face recognition

KW - Hybrid neural method

UR - http://www.scopus.com/inward/record.url?scp=0036880614&partnerID=8YFLogxK

U2 - 10.1109/TSMCA.2003.808252

DO - 10.1109/TSMCA.2003.808252

M3 - Journal article

SN - 1083-4427

VL - 32

SP - 787

EP - 793

JO - IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans.

JF - IEEE Transactions on Systems, Man, and Cybernetics Part A:Systems and Humans.

IS - 6

ER -

A novel face recognition system using hybrid neural and dual eigenspaces methods

Abstract

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this