Facial feature detection using distance vector fields

Stylianos Asteriadis; Nikos Nikolaidis; Ioannis Pitas

doi:10.1016/j.patcog.2009.01.009

Facial feature detection using distance vector fields

Stylianos Asteriadis, Nikos Nikolaidis^*, Ioannis Pitas

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

A novel method for eye and mouth detection and eye center and mouth corner localization, based on geometrical information is presented in this paper. First, a face detector is applied to detect the facial region, and the edge map of this region is calculated. The distance vector field of the face is extracted by assigning to every facial image pixel a vector pointing to the closest edge pixel. The x and y components of these vectors are used to detect the eyes and mouth regions. Luminance information is used for eye center localization, after removing unwanted effects, such as specular highlights, whereas the hue channel of the lip area is used for the detection of the mouth corners. The proposed method has been tested on the XM2VTS and BioID databases, with very good results. © 2009 Elsevier Ltd. All rights reserved.

Original language	English
Pages (from-to)	1388-1398
Number of pages	11
Journal	Pattern Recognition
Volume	42
Issue number	7
DOIs	https://doi.org/10.1016/j.patcog.2009.01.009
Publication status	Published - Jul 2009
Externally published	Yes

Keywords

Distance map
Distance vector field (DVF)
Facial features detection

Access to Document

10.1016/j.patcog.2009.01.009

http://www.mendeley.com/research/facial-feature-detection-using-distance-vector-fields-3

Cite this

@article{14e97581005c4a469894fd682a7b5256,

title = "Facial feature detection using distance vector fields",

abstract = "A novel method for eye and mouth detection and eye center and mouth corner localization, based on geometrical information is presented in this paper. First, a face detector is applied to detect the facial region, and the edge map of this region is calculated. The distance vector field of the face is extracted by assigning to every facial image pixel a vector pointing to the closest edge pixel. The x and y components of these vectors are used to detect the eyes and mouth regions. Luminance information is used for eye center localization, after removing unwanted effects, such as specular highlights, whereas the hue channel of the lip area is used for the detection of the mouth corners. The proposed method has been tested on the XM2VTS and BioID databases, with very good results. {\textcopyright} 2009 Elsevier Ltd. All rights reserved.",

keywords = "Distance map, Distance vector field (DVF), Facial features detection",

author = "Stylianos Asteriadis and Nikos Nikolaidis and Ioannis Pitas",

year = "2009",

month = jul,

doi = "10.1016/j.patcog.2009.01.009",

language = "English",

volume = "42",

pages = "1388--1398",

journal = "Pattern Recognition",

issn = "0031-3203",

publisher = "ELSEVIER SCI LTD",

number = "7",

}

TY - JOUR

T1 - Facial feature detection using distance vector fields

AU - Asteriadis, Stylianos

AU - Nikolaidis, Nikos

AU - Pitas, Ioannis

PY - 2009/7

Y1 - 2009/7

N2 - A novel method for eye and mouth detection and eye center and mouth corner localization, based on geometrical information is presented in this paper. First, a face detector is applied to detect the facial region, and the edge map of this region is calculated. The distance vector field of the face is extracted by assigning to every facial image pixel a vector pointing to the closest edge pixel. The x and y components of these vectors are used to detect the eyes and mouth regions. Luminance information is used for eye center localization, after removing unwanted effects, such as specular highlights, whereas the hue channel of the lip area is used for the detection of the mouth corners. The proposed method has been tested on the XM2VTS and BioID databases, with very good results. © 2009 Elsevier Ltd. All rights reserved.

AB - A novel method for eye and mouth detection and eye center and mouth corner localization, based on geometrical information is presented in this paper. First, a face detector is applied to detect the facial region, and the edge map of this region is calculated. The distance vector field of the face is extracted by assigning to every facial image pixel a vector pointing to the closest edge pixel. The x and y components of these vectors are used to detect the eyes and mouth regions. Luminance information is used for eye center localization, after removing unwanted effects, such as specular highlights, whereas the hue channel of the lip area is used for the detection of the mouth corners. The proposed method has been tested on the XM2VTS and BioID databases, with very good results. © 2009 Elsevier Ltd. All rights reserved.

KW - Distance map

KW - Distance vector field (DVF)

KW - Facial features detection

U2 - 10.1016/j.patcog.2009.01.009

DO - 10.1016/j.patcog.2009.01.009

M3 - Article

SN - 0031-3203

VL - 42

SP - 1388

EP - 1398

JO - Pattern Recognition

JF - Pattern Recognition

IS - 7

ER -