Range image derivatives for GRCM on 2.5D face recognition

Lee Ying Chong, Andrew Beng Jin Teoh, Thian Song Ong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

2.5D face recognition, which leverages both texture and range facial images often outperform sole texture 2D face recognition as the former provides additional unique information than the latter. The 2.5D face recognition naturally incurs higher computational load since two types of data are involved. In this paper, we investigate the possibility of just using range facial image alone for recognition. Gabor-based region covariance matrix (GRCM) is a flexible face feature descriptor that is capable to capture the geometrical and statistical properties of a facial image by fusing the diverse facial features into a covariance matrix. Here, we attempt to extract several feature derivatives from the range facial image for GRCM. Since GRCM resides on the Tensor manifold, geodesic and reparameterized distances of Tensor manifold are used as dissimilarity measures of two GRCMs. Thus, the accuracy performance of range image derivatives with several distance metrics on Tensor manifold is explored. Experimental results show the effectiveness of the range image derivatives and the flexibility of the GRCM in 2.5D face recognition.

Original languageEnglish
Title of host publicationInformation Science and Applications, ICISA 2016
EditorsKuinam J. Kim, Nikolai Joukov
PublisherSpringer Verlag
Pages753-763
Number of pages11
ISBN (Print)9789811005565
DOIs
Publication statusPublished - 2016 Jan 1
EventInternational Conference on Information Science and Applications, ICISA 2016 - Minh City, Viet Nam
Duration: 2016 Feb 152016 Feb 18

Publication series

NameLecture Notes in Electrical Engineering
Volume376
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Other

OtherInternational Conference on Information Science and Applications, ICISA 2016
CountryViet Nam
CityMinh City
Period16/2/1516/2/18

Fingerprint

Face recognition
Covariance matrix
Derivatives
Tensors
Textures

All Science Journal Classification (ASJC) codes

  • Industrial and Manufacturing Engineering

Cite this

Chong, L. Y., Teoh, A. B. J., & Ong, T. S. (2016). Range image derivatives for GRCM on 2.5D face recognition. In K. J. Kim, & N. Joukov (Eds.), Information Science and Applications, ICISA 2016 (pp. 753-763). (Lecture Notes in Electrical Engineering; Vol. 376). Springer Verlag. https://doi.org/10.1007/978-981-10-0557-2_73
Chong, Lee Ying ; Teoh, Andrew Beng Jin ; Ong, Thian Song. / Range image derivatives for GRCM on 2.5D face recognition. Information Science and Applications, ICISA 2016. editor / Kuinam J. Kim ; Nikolai Joukov. Springer Verlag, 2016. pp. 753-763 (Lecture Notes in Electrical Engineering).
@inproceedings{d8b29d2cdb104bd88e202711d9388ac7,
title = "Range image derivatives for GRCM on 2.5D face recognition",
abstract = "2.5D face recognition, which leverages both texture and range facial images often outperform sole texture 2D face recognition as the former provides additional unique information than the latter. The 2.5D face recognition naturally incurs higher computational load since two types of data are involved. In this paper, we investigate the possibility of just using range facial image alone for recognition. Gabor-based region covariance matrix (GRCM) is a flexible face feature descriptor that is capable to capture the geometrical and statistical properties of a facial image by fusing the diverse facial features into a covariance matrix. Here, we attempt to extract several feature derivatives from the range facial image for GRCM. Since GRCM resides on the Tensor manifold, geodesic and reparameterized distances of Tensor manifold are used as dissimilarity measures of two GRCMs. Thus, the accuracy performance of range image derivatives with several distance metrics on Tensor manifold is explored. Experimental results show the effectiveness of the range image derivatives and the flexibility of the GRCM in 2.5D face recognition.",
author = "Chong, {Lee Ying} and Teoh, {Andrew Beng Jin} and Ong, {Thian Song}",
year = "2016",
month = "1",
day = "1",
doi = "10.1007/978-981-10-0557-2_73",
language = "English",
isbn = "9789811005565",
series = "Lecture Notes in Electrical Engineering",
publisher = "Springer Verlag",
pages = "753--763",
editor = "Kim, {Kuinam J.} and Nikolai Joukov",
booktitle = "Information Science and Applications, ICISA 2016",
address = "Germany",

}

Chong, LY, Teoh, ABJ & Ong, TS 2016, Range image derivatives for GRCM on 2.5D face recognition. in KJ Kim & N Joukov (eds), Information Science and Applications, ICISA 2016. Lecture Notes in Electrical Engineering, vol. 376, Springer Verlag, pp. 753-763, International Conference on Information Science and Applications, ICISA 2016, Minh City, Viet Nam, 16/2/15. https://doi.org/10.1007/978-981-10-0557-2_73

Range image derivatives for GRCM on 2.5D face recognition. / Chong, Lee Ying; Teoh, Andrew Beng Jin; Ong, Thian Song.

Information Science and Applications, ICISA 2016. ed. / Kuinam J. Kim; Nikolai Joukov. Springer Verlag, 2016. p. 753-763 (Lecture Notes in Electrical Engineering; Vol. 376).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Range image derivatives for GRCM on 2.5D face recognition

AU - Chong, Lee Ying

AU - Teoh, Andrew Beng Jin

AU - Ong, Thian Song

PY - 2016/1/1

Y1 - 2016/1/1

N2 - 2.5D face recognition, which leverages both texture and range facial images often outperform sole texture 2D face recognition as the former provides additional unique information than the latter. The 2.5D face recognition naturally incurs higher computational load since two types of data are involved. In this paper, we investigate the possibility of just using range facial image alone for recognition. Gabor-based region covariance matrix (GRCM) is a flexible face feature descriptor that is capable to capture the geometrical and statistical properties of a facial image by fusing the diverse facial features into a covariance matrix. Here, we attempt to extract several feature derivatives from the range facial image for GRCM. Since GRCM resides on the Tensor manifold, geodesic and reparameterized distances of Tensor manifold are used as dissimilarity measures of two GRCMs. Thus, the accuracy performance of range image derivatives with several distance metrics on Tensor manifold is explored. Experimental results show the effectiveness of the range image derivatives and the flexibility of the GRCM in 2.5D face recognition.

AB - 2.5D face recognition, which leverages both texture and range facial images often outperform sole texture 2D face recognition as the former provides additional unique information than the latter. The 2.5D face recognition naturally incurs higher computational load since two types of data are involved. In this paper, we investigate the possibility of just using range facial image alone for recognition. Gabor-based region covariance matrix (GRCM) is a flexible face feature descriptor that is capable to capture the geometrical and statistical properties of a facial image by fusing the diverse facial features into a covariance matrix. Here, we attempt to extract several feature derivatives from the range facial image for GRCM. Since GRCM resides on the Tensor manifold, geodesic and reparameterized distances of Tensor manifold are used as dissimilarity measures of two GRCMs. Thus, the accuracy performance of range image derivatives with several distance metrics on Tensor manifold is explored. Experimental results show the effectiveness of the range image derivatives and the flexibility of the GRCM in 2.5D face recognition.

UR - http://www.scopus.com/inward/record.url?scp=84959082903&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959082903&partnerID=8YFLogxK

U2 - 10.1007/978-981-10-0557-2_73

DO - 10.1007/978-981-10-0557-2_73

M3 - Conference contribution

AN - SCOPUS:84959082903

SN - 9789811005565

T3 - Lecture Notes in Electrical Engineering

SP - 753

EP - 763

BT - Information Science and Applications, ICISA 2016

A2 - Kim, Kuinam J.

A2 - Joukov, Nikolai

PB - Springer Verlag

ER -

Chong LY, Teoh ABJ, Ong TS. Range image derivatives for GRCM on 2.5D face recognition. In Kim KJ, Joukov N, editors, Information Science and Applications, ICISA 2016. Springer Verlag. 2016. p. 753-763. (Lecture Notes in Electrical Engineering). https://doi.org/10.1007/978-981-10-0557-2_73