Isoradius Contours: New representations and techniques for 3D face registration and matching

Nick Pears; Tom Heseltine

Isoradius Contours: New representations and techniques for 3D face registration and matching

Nick Pears, Tom Heseltine

Computer Science

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

Abstract

We propose a technique for 3D face registration and matching using a novel representation called "isoradius contours". An isoradius contour is the contour on the 3D facial surface that is a known fixed distance relative to some pre-defined reference point (the tip of the nose). A 3D face representation contains many isoradius contours with different radii and the first major benefit of the technique is that the shape of the contours is independent of the facial pose, due to the infinite rotational symmetry of a sphere. The second major benefit of the technique is that registration, alignment and matching can be implemented using a simple process of ID correlation. Our results have shown that registration and alignment is of comparable accuracy to ICP (iterative closest points), but is fast, non iterative, and is robust to the presence of outliers.

Original language	English
Title of host publication	Third International Symposium on 3D Data Processing, Visualization, and Transmission, Proceedings
Editors	M Pollefeys, K Daniilidis
Place of Publication	LOS ALAMITOS
Publisher	IEEE Computer Society
Pages	176-183
Number of pages	8
ISBN (Print)	978-0-7695-2825-0
Publication status	Published - 2007
Event	3rd International Symposium on 3D Data Processing, Visualization and Transmission - Chapel Hill Duration: 14 Jun 2006 → 16 Jun 2006

Conference

Conference	3rd International Symposium on 3D Data Processing, Visualization and Transmission
City	Chapel Hill
Period	14/06/06 → 16/06/06

Keywords

OBJECT RECOGNITION
FACE

Cite this

@inproceedings{343621af25cd40ce97103a7362b70c98,

title = "Isoradius Contours: New representations and techniques for 3D face registration and matching",

abstract = "We propose a technique for 3D face registration and matching using a novel representation called {"}isoradius contours{"}. An isoradius contour is the contour on the 3D facial surface that is a known fixed distance relative to some pre-defined reference point (the tip of the nose). A 3D face representation contains many isoradius contours with different radii and the first major benefit of the technique is that the shape of the contours is independent of the facial pose, due to the infinite rotational symmetry of a sphere. The second major benefit of the technique is that registration, alignment and matching can be implemented using a simple process of ID correlation. Our results have shown that registration and alignment is of comparable accuracy to ICP (iterative closest points), but is fast, non iterative, and is robust to the presence of outliers.",

keywords = "OBJECT RECOGNITION, FACE",

author = "Nick Pears and Tom Heseltine",

year = "2007",

language = "English",

isbn = "978-0-7695-2825-0",

pages = "176--183",

editor = "M Pollefeys and K Daniilidis",

booktitle = "Third International Symposium on 3D Data Processing, Visualization, and Transmission, Proceedings",

publisher = "IEEE Computer Society",

address = "United States",

note = "3rd International Symposium on 3D Data Processing, Visualization and Transmission ; Conference date: 14-06-2006 Through 16-06-2006",

}

Pears, N & Heseltine, T 2007, Isoradius Contours: New representations and techniques for 3D face registration and matching. in M Pollefeys & K Daniilidis (eds), Third International Symposium on 3D Data Processing, Visualization, and Transmission, Proceedings. IEEE Computer Society, LOS ALAMITOS, pp. 176-183, 3rd International Symposium on 3D Data Processing, Visualization and Transmission, Chapel Hill, 14/06/06.

Isoradius Contours: New representations and techniques for 3D face registration and matching. / Pears, Nick; Heseltine, Tom.

Third International Symposium on 3D Data Processing, Visualization, and Transmission, Proceedings. ed. / M Pollefeys; K Daniilidis. LOS ALAMITOS : IEEE Computer Society, 2007. p. 176-183.

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

TY - GEN

T1 - Isoradius Contours: New representations and techniques for 3D face registration and matching

AU - Pears, Nick

AU - Heseltine, Tom

PY - 2007

Y1 - 2007

N2 - We propose a technique for 3D face registration and matching using a novel representation called "isoradius contours". An isoradius contour is the contour on the 3D facial surface that is a known fixed distance relative to some pre-defined reference point (the tip of the nose). A 3D face representation contains many isoradius contours with different radii and the first major benefit of the technique is that the shape of the contours is independent of the facial pose, due to the infinite rotational symmetry of a sphere. The second major benefit of the technique is that registration, alignment and matching can be implemented using a simple process of ID correlation. Our results have shown that registration and alignment is of comparable accuracy to ICP (iterative closest points), but is fast, non iterative, and is robust to the presence of outliers.

AB - We propose a technique for 3D face registration and matching using a novel representation called "isoradius contours". An isoradius contour is the contour on the 3D facial surface that is a known fixed distance relative to some pre-defined reference point (the tip of the nose). A 3D face representation contains many isoradius contours with different radii and the first major benefit of the technique is that the shape of the contours is independent of the facial pose, due to the infinite rotational symmetry of a sphere. The second major benefit of the technique is that registration, alignment and matching can be implemented using a simple process of ID correlation. Our results have shown that registration and alignment is of comparable accuracy to ICP (iterative closest points), but is fast, non iterative, and is robust to the presence of outliers.

KW - OBJECT RECOGNITION

KW - FACE

M3 - Conference contribution

SN - 978-0-7695-2825-0

SP - 176

EP - 183

BT - Third International Symposium on 3D Data Processing, Visualization, and Transmission, Proceedings

A2 - Pollefeys, M

A2 - Daniilidis, K

PB - IEEE Computer Society

CY - LOS ALAMITOS

T2 - 3rd International Symposium on 3D Data Processing, Visualization and Transmission

Y2 - 14 June 2006 through 16 June 2006

ER -