Fusing horizontal and vertical components of face images for identity verification

Beom Seok Oh; Byung Gue Choi; Kar Ann Toh

doi:10.1109/ICIEA.2009.5138286

Fusing horizontal and vertical components of face images for identity verification

Beom Seok Oh, Byung Gue Choi, Kar Ann Toh

Department of Electrical and Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

This paper presents an empirical investigation of two sparse random projections which correspond to extraction of vertical and horizontal features from a face image for identity verification. In order to enhance the performance of each projection, the matching scores of both directional features are fused via a Total Error Rate minimization. The BERC face database is used for evaluating the effectiveness of the proposed method. Our empirical results show that the proposed vertical projection outperforms the commonly used PCA and a Random Projection algorithm in terms of the Equal Error Rate (EER) measure. The result of fusion shows an even better EER performance than that from each individual projection.

Original language	English
Title of host publication	2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009
Pages	651-655
Number of pages	5
DOIs	https://doi.org/10.1109/ICIEA.2009.5138286
Publication status	Published - 2009
Event	2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009 - Xi'an, China Duration: 2009 May 25 → 2009 May 27

Publication series

Name	2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009

Other

Other	2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009
Country/Territory	China
City	Xi'an
Period	09/5/25 → 09/5/27

All Science Journal Classification (ASJC) codes

Artificial Intelligence
Computer Networks and Communications
Control and Systems Engineering
Electrical and Electronic Engineering

Access to Document

10.1109/ICIEA.2009.5138286

Cite this

@inproceedings{2e65040f16ae4067925290d08f2e9976,

title = "Fusing horizontal and vertical components of face images for identity verification",

abstract = "This paper presents an empirical investigation of two sparse random projections which correspond to extraction of vertical and horizontal features from a face image for identity verification. In order to enhance the performance of each projection, the matching scores of both directional features are fused via a Total Error Rate minimization. The BERC face database is used for evaluating the effectiveness of the proposed method. Our empirical results show that the proposed vertical projection outperforms the commonly used PCA and a Random Projection algorithm in terms of the Equal Error Rate (EER) measure. The result of fusion shows an even better EER performance than that from each individual projection.",

author = "Oh, {Beom Seok} and Choi, {Byung Gue} and Toh, {Kar Ann}",

year = "2009",

doi = "10.1109/ICIEA.2009.5138286",

language = "English",

isbn = "9781424428007",

series = "2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009",

pages = "651--655",

booktitle = "2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009",

note = "2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009 ; Conference date: 25-05-2009 Through 27-05-2009",

}

Oh, BS, Choi, BG & Toh, KA 2009, Fusing horizontal and vertical components of face images for identity verification. in 2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009., 5138286, 2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009, pp. 651-655, 2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009, Xi'an, China, 09/5/25. https://doi.org/10.1109/ICIEA.2009.5138286

Fusing horizontal and vertical components of face images for identity verification. / Oh, Beom Seok; Choi, Byung Gue; Toh, Kar Ann.
2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009. 2009. p. 651-655 5138286 (2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Fusing horizontal and vertical components of face images for identity verification

AU - Oh, Beom Seok

AU - Choi, Byung Gue

AU - Toh, Kar Ann

PY - 2009

Y1 - 2009

N2 - This paper presents an empirical investigation of two sparse random projections which correspond to extraction of vertical and horizontal features from a face image for identity verification. In order to enhance the performance of each projection, the matching scores of both directional features are fused via a Total Error Rate minimization. The BERC face database is used for evaluating the effectiveness of the proposed method. Our empirical results show that the proposed vertical projection outperforms the commonly used PCA and a Random Projection algorithm in terms of the Equal Error Rate (EER) measure. The result of fusion shows an even better EER performance than that from each individual projection.

AB - This paper presents an empirical investigation of two sparse random projections which correspond to extraction of vertical and horizontal features from a face image for identity verification. In order to enhance the performance of each projection, the matching scores of both directional features are fused via a Total Error Rate minimization. The BERC face database is used for evaluating the effectiveness of the proposed method. Our empirical results show that the proposed vertical projection outperforms the commonly used PCA and a Random Projection algorithm in terms of the Equal Error Rate (EER) measure. The result of fusion shows an even better EER performance than that from each individual projection.

UR - http://www.scopus.com/inward/record.url?scp=70349325778&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349325778&partnerID=8YFLogxK

U2 - 10.1109/ICIEA.2009.5138286

DO - 10.1109/ICIEA.2009.5138286

M3 - Conference contribution

AN - SCOPUS:70349325778

SN - 9781424428007

T3 - 2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009

SP - 651

EP - 655

BT - 2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009

T2 - 2009 4th IEEE Conference on Industrial Electronics and Applications, ICIEA 2009

Y2 - 25 May 2009 through 27 May 2009

ER -

Fusing horizontal and vertical components of face images for identity verification

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this