Landmark Localisation in 3D Face Data

Marcelo Romero; Nick Pears

doi:10.1109/AVSS.2009.90

Landmark Localisation in 3D Face Data

Marcelo Romero, Nick Pears

Computer Science

Research output: Contribution to conference › Paper › peer-review

Abstract

A comparison of several approaches that use graph matching and cascade filtering for landmark localization in 3D face data is presented. For the first method, we apply the structural graph matching algorithm ldquorelaxation by eliminationrdquo using a simple ldquodistance to local planerdquo node property and a ldquoEuclidean distancerdquo arc property. After the graph matching process has eliminated unlikely candidates, the most likely triplet is selected, by exhaustive search, as the minimum Mahalanobis distance over a six dimensional space, corresponding to three node variables and three arc variables. A second method uses state-of-the-art pose-invariant feature descriptors embedded into a cascade filter to localize the nose tip. After that, local graph matching is applied to localize the inner eye corners. We evaluate our systems by computing root mean square errors of estimated landmark locations against ground truth landmark localizations within the 3D Face Recognition Grand Challenge database. Our best system, which uses a novel pose-invariant shape descriptor, scores 99.77% successful localization of the nose and 96.82% successful localization of the eyes.

Original language	Undefined/Unknown
Pages	73-78
DOIs	https://doi.org/10.1109/AVSS.2009.90
Publication status	Published - 2009

Access to Document

10.1109/AVSS.2009.90

http://dx.doi.org/10.1109/AVSS.2009.90

Cite this

@conference{6c8db1dae26c4af492e3139779887315,

title = "Landmark Localisation in 3D Face Data",

abstract = "A comparison of several approaches that use graph matching and cascade filtering for landmark localization in 3D face data is presented. For the first method, we apply the structural graph matching algorithm ldquorelaxation by eliminationrdquo using a simple ldquodistance to local planerdquo node property and a ldquoEuclidean distancerdquo arc property. After the graph matching process has eliminated unlikely candidates, the most likely triplet is selected, by exhaustive search, as the minimum Mahalanobis distance over a six dimensional space, corresponding to three node variables and three arc variables. A second method uses state-of-the-art pose-invariant feature descriptors embedded into a cascade filter to localize the nose tip. After that, local graph matching is applied to localize the inner eye corners. We evaluate our systems by computing root mean square errors of estimated landmark locations against ground truth landmark localizations within the 3D Face Recognition Grand Challenge database. Our best system, which uses a novel pose-invariant shape descriptor, scores 99.77% successful localization of the nose and 96.82% successful localization of the eyes.",

author = "Marcelo Romero and Nick Pears",

year = "2009",

doi = "10.1109/AVSS.2009.90",

language = "Undefined/Unknown",

pages = "73--78",

}

TY - CONF

T1 - Landmark Localisation in 3D Face Data

AU - Romero, Marcelo

AU - Pears, Nick

PY - 2009

Y1 - 2009

N2 - A comparison of several approaches that use graph matching and cascade filtering for landmark localization in 3D face data is presented. For the first method, we apply the structural graph matching algorithm ldquorelaxation by eliminationrdquo using a simple ldquodistance to local planerdquo node property and a ldquoEuclidean distancerdquo arc property. After the graph matching process has eliminated unlikely candidates, the most likely triplet is selected, by exhaustive search, as the minimum Mahalanobis distance over a six dimensional space, corresponding to three node variables and three arc variables. A second method uses state-of-the-art pose-invariant feature descriptors embedded into a cascade filter to localize the nose tip. After that, local graph matching is applied to localize the inner eye corners. We evaluate our systems by computing root mean square errors of estimated landmark locations against ground truth landmark localizations within the 3D Face Recognition Grand Challenge database. Our best system, which uses a novel pose-invariant shape descriptor, scores 99.77% successful localization of the nose and 96.82% successful localization of the eyes.

AB - A comparison of several approaches that use graph matching and cascade filtering for landmark localization in 3D face data is presented. For the first method, we apply the structural graph matching algorithm ldquorelaxation by eliminationrdquo using a simple ldquodistance to local planerdquo node property and a ldquoEuclidean distancerdquo arc property. After the graph matching process has eliminated unlikely candidates, the most likely triplet is selected, by exhaustive search, as the minimum Mahalanobis distance over a six dimensional space, corresponding to three node variables and three arc variables. A second method uses state-of-the-art pose-invariant feature descriptors embedded into a cascade filter to localize the nose tip. After that, local graph matching is applied to localize the inner eye corners. We evaluate our systems by computing root mean square errors of estimated landmark locations against ground truth landmark localizations within the 3D Face Recognition Grand Challenge database. Our best system, which uses a novel pose-invariant shape descriptor, scores 99.77% successful localization of the nose and 96.82% successful localization of the eyes.

UR - http://www.scopus.com/inward/record.url?scp=72349095000&partnerID=8YFLogxK

U2 - 10.1109/AVSS.2009.90

DO - 10.1109/AVSS.2009.90

M3 - Paper

SP - 73

EP - 78

ER -

Landmark Localisation in 3D Face Data

Abstract

Access to Document

Other files and links

Cite this