Three-dimensional face recognition using combinations of surface feature map subspace components

Thomas Heseltine; Nick Pears; Jim Austin

doi:10.1016/j.imavis.2006.12.008

Three-dimensional face recognition using combinations of surface feature map subspace components

Thomas Heseltine, Nick Pears, Jim Austin

Computer Science

Research output: Contribution to journal › Article › peer-review

Abstract

In this paper, we show the effect of using a variety of facial surface feature maps within the Fishersurface technique, which uses linear discriminant analysis, and suggest a method of identifying and extracting useful qualities offered by each surface feature map. Combining these multi-feature subspace components into a unified surface subspace, we create a three-dimensional face recognition system producing significantly lower error rates than individual surface feature map systems tested on the same data. We evaluate systems by performing up to 1,079,715 verification operations on a large test set of 3D face models. Results are presented in the form of false acceptance and false rejection rates, generated by varying a decision threshold applied to a distance metric in surface space.

Original language	English
Pages (from-to)	382-396
Number of pages	15
Journal	Image and Vision Computing
Volume	26
Issue number	3
DOIs	https://doi.org/10.1016/j.imavis.2006.12.008
Publication status	Published - 3 Mar 2008

Access to Document

10.1016/j.imavis.2006.12.008

http://www.sciencedirect.com/science/article/pii/S0262885606003519

Cite this

@article{d40175ef520c4c1eb3ae101832fd4fd8,

title = "Three-dimensional face recognition using combinations of surface feature map subspace components",

abstract = "In this paper, we show the effect of using a variety of facial surface feature maps within the Fishersurface technique, which uses linear discriminant analysis, and suggest a method of identifying and extracting useful qualities offered by each surface feature map. Combining these multi-feature subspace components into a unified surface subspace, we create a three-dimensional face recognition system producing significantly lower error rates than individual surface feature map systems tested on the same data. We evaluate systems by performing up to 1,079,715 verification operations on a large test set of 3D face models. Results are presented in the form of false acceptance and false rejection rates, generated by varying a decision threshold applied to a distance metric in surface space.",

author = "Thomas Heseltine and Nick Pears and Jim Austin",

year = "2008",

month = mar,

day = "3",

doi = "10.1016/j.imavis.2006.12.008",

language = "English",

volume = "26",

pages = "382--396",

journal = "Image and Vision Computing",

issn = "0262-8856",

publisher = "Elsevier",

number = "3",

}

TY - JOUR

T1 - Three-dimensional face recognition using combinations of surface feature map subspace components

AU - Heseltine, Thomas

AU - Pears, Nick

AU - Austin, Jim

PY - 2008/3/3

Y1 - 2008/3/3

N2 - In this paper, we show the effect of using a variety of facial surface feature maps within the Fishersurface technique, which uses linear discriminant analysis, and suggest a method of identifying and extracting useful qualities offered by each surface feature map. Combining these multi-feature subspace components into a unified surface subspace, we create a three-dimensional face recognition system producing significantly lower error rates than individual surface feature map systems tested on the same data. We evaluate systems by performing up to 1,079,715 verification operations on a large test set of 3D face models. Results are presented in the form of false acceptance and false rejection rates, generated by varying a decision threshold applied to a distance metric in surface space.

AB - In this paper, we show the effect of using a variety of facial surface feature maps within the Fishersurface technique, which uses linear discriminant analysis, and suggest a method of identifying and extracting useful qualities offered by each surface feature map. Combining these multi-feature subspace components into a unified surface subspace, we create a three-dimensional face recognition system producing significantly lower error rates than individual surface feature map systems tested on the same data. We evaluate systems by performing up to 1,079,715 verification operations on a large test set of 3D face models. Results are presented in the form of false acceptance and false rejection rates, generated by varying a decision threshold applied to a distance metric in surface space.

UR - http://www.scopus.com/inward/record.url?scp=36549063743&partnerID=8YFLogxK

U2 - 10.1016/j.imavis.2006.12.008

DO - 10.1016/j.imavis.2006.12.008

M3 - Article

SN - 0262-8856

VL - 26

SP - 382

EP - 396

JO - Image and Vision Computing

JF - Image and Vision Computing

IS - 3

ER -

Three-dimensional face recognition using combinations of surface feature map subspace components

Abstract

Access to Document

Other files and links

Cite this