Likelihood Ratio-Based Detection of Facial Features

A.M. Bazen; Raymond N.J. Veldhuis; Gerrie H. Croonen

Likelihood Ratio-Based Detection of Facial Features

A.M. Bazen, Raymond N.J. Veldhuis, Gerrie H. Croonen

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

72 Downloads (Pure)

Abstract

One of the first steps in face recognition, after image acquisition, is registration. A simple but effective technique of registration is to align facial features, such as eyes, nose and mouth, as well as possible to a standard face. This requires an accurate automatic estimate of the locations of those features. This contribution proposes a method for estimating the locations of facial features based on likelihood ratio-based detection. A post-processing step that evaluates the topology of the facial features is added to reduce the number of false detections. Although the individual detectors only have a reasonable performance (equal error rates range from 3.3% for the eyes to 1.0% for the nose), the positions of the facial features are estimated correctly in 95% of the face images.

Original language	Undefined
Title of host publication	14th Annual Workshop on Circuits Systems and Signal Processing (ProRISC)
Place of Publication	Utrecht, The Netherlands
Publisher	STW
Pages	323-329
Number of pages	7
ISBN (Print)	90-73461-39-1
Publication status	Published - Nov 2003
Event	14th ProRISC Workshop on Circuits, Systems and Signal Processing 2003 - Veldhoven, Netherlands Duration: 25 Nov 2003 → 27 Nov 2003 Conference number: 14

Workshop

Workshop	14th ProRISC Workshop on Circuits, Systems and Signal Processing 2003
Abbreviated title	ProRISC
Country/Territory	Netherlands
City	Veldhoven
Period	25/11/03 → 27/11/03

Keywords

EWI-813
SCS-Safety
METIS-215836
IR-46702
Likelihood Ratio
Face Recognition
Registration
facial feature detection

Access to Document

Cite this

@inproceedings{657003407fe546aeaf4995ef80f41787,

title = "Likelihood Ratio-Based Detection of Facial Features",

abstract = "One of the first steps in face recognition, after image acquisition, is registration. A simple but effective technique of registration is to align facial features, such as eyes, nose and mouth, as well as possible to a standard face. This requires an accurate automatic estimate of the locations of those features. This contribution proposes a method for estimating the locations of facial features based on likelihood ratio-based detection. A post-processing step that evaluates the topology of the facial features is added to reduce the number of false detections. Although the individual detectors only have a reasonable performance (equal error rates range from 3.3% for the eyes to 1.0% for the nose), the positions of the facial features are estimated correctly in 95% of the face images.",

keywords = "EWI-813, SCS-Safety, METIS-215836, IR-46702, Likelihood Ratio, Face Recognition, Registration, facial feature detection",

author = "A.M. Bazen and Veldhuis, {Raymond N.J.} and Croonen, {Gerrie H.}",

note = "Imported from DIES; 14th ProRISC Workshop on Circuits, Systems and Signal Processing 2003 ; Conference date: 25-11-2003 Through 27-11-2003",

year = "2003",

month = nov,

language = "Undefined",

isbn = "90-73461-39-1",

pages = "323--329",

booktitle = "14th Annual Workshop on Circuits Systems and Signal Processing (ProRISC)",

publisher = "STW",

}

TY - GEN

T1 - Likelihood Ratio-Based Detection of Facial Features

AU - Bazen, A.M.

AU - Veldhuis, Raymond N.J.

AU - Croonen, Gerrie H.

N1 - Conference code: 14

PY - 2003/11

Y1 - 2003/11

N2 - One of the first steps in face recognition, after image acquisition, is registration. A simple but effective technique of registration is to align facial features, such as eyes, nose and mouth, as well as possible to a standard face. This requires an accurate automatic estimate of the locations of those features. This contribution proposes a method for estimating the locations of facial features based on likelihood ratio-based detection. A post-processing step that evaluates the topology of the facial features is added to reduce the number of false detections. Although the individual detectors only have a reasonable performance (equal error rates range from 3.3% for the eyes to 1.0% for the nose), the positions of the facial features are estimated correctly in 95% of the face images.

AB - One of the first steps in face recognition, after image acquisition, is registration. A simple but effective technique of registration is to align facial features, such as eyes, nose and mouth, as well as possible to a standard face. This requires an accurate automatic estimate of the locations of those features. This contribution proposes a method for estimating the locations of facial features based on likelihood ratio-based detection. A post-processing step that evaluates the topology of the facial features is added to reduce the number of false detections. Although the individual detectors only have a reasonable performance (equal error rates range from 3.3% for the eyes to 1.0% for the nose), the positions of the facial features are estimated correctly in 95% of the face images.

KW - EWI-813

KW - SCS-Safety

KW - METIS-215836

KW - IR-46702

KW - Likelihood Ratio

KW - Face Recognition

KW - Registration

KW - facial feature detection

M3 - Conference contribution

SN - 90-73461-39-1

SP - 323

EP - 329

BT - 14th Annual Workshop on Circuits Systems and Signal Processing (ProRISC)

PB - STW

CY - Utrecht, The Netherlands

T2 - 14th ProRISC Workshop on Circuits, Systems and Signal Processing 2003

Y2 - 25 November 2003 through 27 November 2003

ER -