Face set classification using maximally probable mutual modes

Oggie Arandelovic; Roberto Cipolla

doi:10.1109/ICPR.2006.535

Face set classification using maximally probable mutual modes

Oggie Arandelovic^*, Roberto Cipolla

^*Corresponding author for this work

School of Computer Science

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

Abstract

In this paper we consider face recognition from sets of face images and, in particular, recognition invariance to illumination. The main contribution is an algorithm based on the novel concept of Maximally Probable Mutual Modes (MMPM). Specifically: (i) we discuss and derive a local manifold illumination invariant and (ii) show how the invariant naturally leads to a formulation of "common modes" of two face appearance distributions. Recognition is then performed by finding the most probable mode, which is shown to be an eigenvalue problem. The effectiveness of the proposed method is demonstrated empirically on a challenging database containing the total of 700 video sequences of 100 individuals.

Original language	English
Title of host publication	Proceedings - International Conference on Pattern Recognition
Pages	511-514
Number of pages	4
Volume	1
DOIs	https://doi.org/10.1109/ICPR.2006.535
Publication status	Published - 2006
Event	18th International Conference on Pattern Recognition, ICPR 2006 - Hong Kong, China Duration: 20 Aug 2006 → 24 Aug 2006

Conference

Conference	18th International Conference on Pattern Recognition, ICPR 2006
Country/Territory	China
City	Hong Kong
Period	20/08/06 → 24/08/06

Access to Document

10.1109/ICPR.2006.535

Cite this

@inproceedings{6c4596da66b747628cda3318816b817c,

title = "Face set classification using maximally probable mutual modes",

abstract = "In this paper we consider face recognition from sets of face images and, in particular, recognition invariance to illumination. The main contribution is an algorithm based on the novel concept of Maximally Probable Mutual Modes (MMPM). Specifically: (i) we discuss and derive a local manifold illumination invariant and (ii) show how the invariant naturally leads to a formulation of {"}common modes{"} of two face appearance distributions. Recognition is then performed by finding the most probable mode, which is shown to be an eigenvalue problem. The effectiveness of the proposed method is demonstrated empirically on a challenging database containing the total of 700 video sequences of 100 individuals.",

author = "Oggie Arandelovic and Roberto Cipolla",

year = "2006",

doi = "10.1109/ICPR.2006.535",

language = "English",

isbn = "0769525210",

volume = "1",

pages = "511--514",

booktitle = "Proceedings - International Conference on Pattern Recognition",

note = "18th International Conference on Pattern Recognition, ICPR 2006 ; Conference date: 20-08-2006 Through 24-08-2006",

}

TY - GEN

T1 - Face set classification using maximally probable mutual modes

AU - Arandelovic, Oggie

AU - Cipolla, Roberto

PY - 2006

Y1 - 2006

N2 - In this paper we consider face recognition from sets of face images and, in particular, recognition invariance to illumination. The main contribution is an algorithm based on the novel concept of Maximally Probable Mutual Modes (MMPM). Specifically: (i) we discuss and derive a local manifold illumination invariant and (ii) show how the invariant naturally leads to a formulation of "common modes" of two face appearance distributions. Recognition is then performed by finding the most probable mode, which is shown to be an eigenvalue problem. The effectiveness of the proposed method is demonstrated empirically on a challenging database containing the total of 700 video sequences of 100 individuals.

AB - In this paper we consider face recognition from sets of face images and, in particular, recognition invariance to illumination. The main contribution is an algorithm based on the novel concept of Maximally Probable Mutual Modes (MMPM). Specifically: (i) we discuss and derive a local manifold illumination invariant and (ii) show how the invariant naturally leads to a formulation of "common modes" of two face appearance distributions. Recognition is then performed by finding the most probable mode, which is shown to be an eigenvalue problem. The effectiveness of the proposed method is demonstrated empirically on a challenging database containing the total of 700 video sequences of 100 individuals.

UR - http://www.scopus.com/inward/record.url?scp=34047229436&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2006.535

DO - 10.1109/ICPR.2006.535

M3 - Conference contribution

AN - SCOPUS:34047229436

SN - 0769525210

SN - 9780769525211

VL - 1

SP - 511

EP - 514

BT - Proceedings - International Conference on Pattern Recognition

T2 - 18th International Conference on Pattern Recognition, ICPR 2006

Y2 - 20 August 2006 through 24 August 2006

ER -

Face set classification using maximally probable mutual modes

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this