Face recognition from face motion manifolds using robust kernel resistor-average distance

Oggie Arandelovic; Roberto Cipolla

doi:10.1109/CVPR.2004.341

Face recognition from face motion manifolds using robust kernel resistor-average distance

Oggie Arandelovic, Roberto Cipolla

School of Computer Science

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

Abstract

In this work we consider face recognition from face motion manifolds. An information-theoretic approach with Resistor-Average Distance (RAD) as a dissimilarity measure between distributions of face images is proposed. We introduce a kernel-based algorithm that retains the simplicity of the closed-form expression for the RAD between two normal distributions, while allowing for modelling of complex, nonlinear manifolds. Additionally, it is shown how errors in the face registration process can be modelled to significantly improve recognition. Recognition performance of our method is experimentally demonstrated and shown to outperform state-of-the-art algorithms. Recognition rates of 97-100% are consistently achieved on databases of 35-90 people.

Original language	English
Title of host publication	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Publisher	IEEE Computer Society
Volume	2004-January
Edition	January
DOIs	https://doi.org/10.1109/CVPR.2004.341
Publication status	Published - 2004
Event	2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004 - Washington, United States Duration: 27 Jun 2004 → 2 Jul 2004

Conference

Conference	2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004
Country/Territory	United States
City	Washington
Period	27/06/04 → 2/07/04

Access to Document

10.1109/CVPR.2004.341

Cite this

@inproceedings{12c3a35dd37e4600aa671d420b8c7c53,

title = "Face recognition from face motion manifolds using robust kernel resistor-average distance",

abstract = "In this work we consider face recognition from face motion manifolds. An information-theoretic approach with Resistor-Average Distance (RAD) as a dissimilarity measure between distributions of face images is proposed. We introduce a kernel-based algorithm that retains the simplicity of the closed-form expression for the RAD between two normal distributions, while allowing for modelling of complex, nonlinear manifolds. Additionally, it is shown how errors in the face registration process can be modelled to significantly improve recognition. Recognition performance of our method is experimentally demonstrated and shown to outperform state-of-the-art algorithms. Recognition rates of 97-100% are consistently achieved on databases of 35-90 people.",

author = "Oggie Arandelovic and Roberto Cipolla",

year = "2004",

doi = "10.1109/CVPR.2004.341",

language = "English",

volume = "2004-January",

booktitle = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops",

publisher = "IEEE Computer Society",

address = "United States",

edition = "January",

note = "2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004 ; Conference date: 27-06-2004 Through 02-07-2004",

}

Arandelovic, O & Cipolla, R 2004, Face recognition from face motion manifolds using robust kernel resistor-average distance. in IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. January edn, vol. 2004-January, 1384881, IEEE Computer Society, 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004, Washington, United States, 27/06/04. https://doi.org/10.1109/CVPR.2004.341

Face recognition from face motion manifolds using robust kernel resistor-average distance. / Arandelovic, Oggie; Cipolla, Roberto.
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops. Vol. 2004-January January. ed. IEEE Computer Society, 2004. 1384881.

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

TY - GEN

T1 - Face recognition from face motion manifolds using robust kernel resistor-average distance

AU - Arandelovic, Oggie

AU - Cipolla, Roberto

PY - 2004

Y1 - 2004

N2 - In this work we consider face recognition from face motion manifolds. An information-theoretic approach with Resistor-Average Distance (RAD) as a dissimilarity measure between distributions of face images is proposed. We introduce a kernel-based algorithm that retains the simplicity of the closed-form expression for the RAD between two normal distributions, while allowing for modelling of complex, nonlinear manifolds. Additionally, it is shown how errors in the face registration process can be modelled to significantly improve recognition. Recognition performance of our method is experimentally demonstrated and shown to outperform state-of-the-art algorithms. Recognition rates of 97-100% are consistently achieved on databases of 35-90 people.

AB - In this work we consider face recognition from face motion manifolds. An information-theoretic approach with Resistor-Average Distance (RAD) as a dissimilarity measure between distributions of face images is proposed. We introduce a kernel-based algorithm that retains the simplicity of the closed-form expression for the RAD between two normal distributions, while allowing for modelling of complex, nonlinear manifolds. Additionally, it is shown how errors in the face registration process can be modelled to significantly improve recognition. Recognition performance of our method is experimentally demonstrated and shown to outperform state-of-the-art algorithms. Recognition rates of 97-100% are consistently achieved on databases of 35-90 people.

UR - http://www.scopus.com/inward/record.url?scp=84932646555&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2004.341

DO - 10.1109/CVPR.2004.341

M3 - Conference contribution

AN - SCOPUS:84932646555

VL - 2004-January

BT - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

PB - IEEE Computer Society

T2 - 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2004

Y2 - 27 June 2004 through 2 July 2004

ER -

Face recognition from face motion manifolds using robust kernel resistor-average distance

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this