Human face recognition by adaptive processing of tree structures representation

Siu Yeung Cho; Jia Jun Wong

doi:10.1007/s00521-007-0108-8

Human face recognition by adaptive processing of tree structures representation

Siu Yeung Cho, Jia Jun Wong

Research output: Journal Publication › Article › peer-review

3 Citations (Scopus)

Abstract

This paper describes a novel method of facial representation and recognition based upon adaptive processing of tree structures. Instead of the conventional flat vector representation for a face, a neural network approach-based technique is proposed to transform the Localised Gabor Feature (LGF) vectors extracted from human facial components into Human Face Tree Structure (HFTS) to represent a human face. A structural training algorithm is assigned to train and recognize the face identity in this HFTS representation with the corresponding LGF vectors. By benchmarking using the tested public face databases presented in this paper, our approach is able to achieve accuracy up to 90% under different scenarios of lighting conditions and posture orientations.

Original language	English
Pages (from-to)	201-215
Number of pages	15
Journal	Neural Computing and Applications
Volume	17
Issue number	3
DOIs	https://doi.org/10.1007/s00521-007-0108-8
Publication status	Published - Jun 2008
Externally published	Yes

Keywords

Adaptive processing of data structures
Face recognition
Gabor feature extraction
Neural network

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1007/s00521-007-0108-8

Cite this

@article{94282569f1fb4c0c80b9505dd6c1b3ed,

title = "Human face recognition by adaptive processing of tree structures representation",

abstract = "This paper describes a novel method of facial representation and recognition based upon adaptive processing of tree structures. Instead of the conventional flat vector representation for a face, a neural network approach-based technique is proposed to transform the Localised Gabor Feature (LGF) vectors extracted from human facial components into Human Face Tree Structure (HFTS) to represent a human face. A structural training algorithm is assigned to train and recognize the face identity in this HFTS representation with the corresponding LGF vectors. By benchmarking using the tested public face databases presented in this paper, our approach is able to achieve accuracy up to 90% under different scenarios of lighting conditions and posture orientations.",

keywords = "Adaptive processing of data structures, Face recognition, Gabor feature extraction, Neural network",

author = "Cho, {Siu Yeung} and Wong, {Jia Jun}",

note = "Funding Information: This work is supported by the NTU SCE start-up grant (CE-SUG 10/03). ",

year = "2008",

month = jun,

doi = "10.1007/s00521-007-0108-8",

language = "English",

volume = "17",

pages = "201--215",

journal = "Neural Computing and Applications",

issn = "0941-0643",

publisher = "Springer London",

number = "3",

}

TY - JOUR

T1 - Human face recognition by adaptive processing of tree structures representation

AU - Cho, Siu Yeung

AU - Wong, Jia Jun

N1 - Funding Information: This work is supported by the NTU SCE start-up grant (CE-SUG 10/03).

PY - 2008/6

Y1 - 2008/6

N2 - This paper describes a novel method of facial representation and recognition based upon adaptive processing of tree structures. Instead of the conventional flat vector representation for a face, a neural network approach-based technique is proposed to transform the Localised Gabor Feature (LGF) vectors extracted from human facial components into Human Face Tree Structure (HFTS) to represent a human face. A structural training algorithm is assigned to train and recognize the face identity in this HFTS representation with the corresponding LGF vectors. By benchmarking using the tested public face databases presented in this paper, our approach is able to achieve accuracy up to 90% under different scenarios of lighting conditions and posture orientations.

AB - This paper describes a novel method of facial representation and recognition based upon adaptive processing of tree structures. Instead of the conventional flat vector representation for a face, a neural network approach-based technique is proposed to transform the Localised Gabor Feature (LGF) vectors extracted from human facial components into Human Face Tree Structure (HFTS) to represent a human face. A structural training algorithm is assigned to train and recognize the face identity in this HFTS representation with the corresponding LGF vectors. By benchmarking using the tested public face databases presented in this paper, our approach is able to achieve accuracy up to 90% under different scenarios of lighting conditions and posture orientations.

KW - Adaptive processing of data structures

KW - Face recognition

KW - Gabor feature extraction

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=42549130330&partnerID=8YFLogxK

U2 - 10.1007/s00521-007-0108-8

DO - 10.1007/s00521-007-0108-8

M3 - Article

AN - SCOPUS:42549130330

SN - 0941-0643

VL - 17

SP - 201

EP - 215

JO - Neural Computing and Applications

JF - Neural Computing and Applications

IS - 3

ER -

Human face recognition by adaptive processing of tree structures representation

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this