Facial Component Detection in Thermal Imagery

Brais Martinez; Xavier Binefa; Maja Pantic

doi:10.1109/CVPRW.2010.5543605

Facial Component Detection in Thermal Imagery

Brais Martinez, Xavier Binefa, Maja Pantic

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

27 Citations (Scopus)

150 Downloads (Pure)

Abstract

This paper studies the problem of detecting facial components in thermal imagery (specifically eyes, nostrils and mouth). One of the immediate goals is to enable the automatic registration of facial thermal images. The detection of eyes and nostrils is performed using Haar features and the GentleBoost algorithm, which are shown to provide superior detection rates. The detection of the mouth is based on the detections of the eyes and the nostrils and is performed using measures of entropy and self similarity. The results show that reliable facial component detection is feasible using this methodology, getting a correct detection rate for both eyes and nostrils of 0.8. A correct eyes and nostrils detection enables a correct detection of the mouth in 65% of closed-mouth test images and in 73% of open-mouth test images.

Original language	Undefined
Title of host publication	IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2010, Workshop on Object Tracking & Classification Beyond and in the Visible Spectrum
Place of Publication	USA
Publisher	IEEE
Pages	48-54
Number of pages	7
ISBN (Print)	978-1-4244-7029-7
DOIs	https://doi.org/10.1109/CVPRW.2010.5543605
Publication status	Published - 14 Jun 2010
Event	23rd IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010 - San Francisco, United States Duration: 13 Jun 2010 → 18 Jun 2010 Conference number: 23

Publication series

Name
Publisher	IEEE Computer Society
Volume	3

Workshop

Workshop	23rd IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010
Abbreviated title	CVPR 2010
Country/Territory	United States
City	San Francisco
Period	13/06/10 → 18/06/10

Keywords

METIS-276369
EWI-19562
HMI-MI: MULTIMODAL INTERACTIONS
IR-75977

Access to Document

10.1109/CVPRW.2010.5543605

Cite this

@inproceedings{9e64d55d5b814150b445c72fa465f82f,

title = "Facial Component Detection in Thermal Imagery",

abstract = "This paper studies the problem of detecting facial components in thermal imagery (specifically eyes, nostrils and mouth). One of the immediate goals is to enable the automatic registration of facial thermal images. The detection of eyes and nostrils is performed using Haar features and the GentleBoost algorithm, which are shown to provide superior detection rates. The detection of the mouth is based on the detections of the eyes and the nostrils and is performed using measures of entropy and self similarity. The results show that reliable facial component detection is feasible using this methodology, getting a correct detection rate for both eyes and nostrils of 0.8. A correct eyes and nostrils detection enables a correct detection of the mouth in 65% of closed-mouth test images and in 73% of open-mouth test images.",

keywords = "METIS-276369, EWI-19562, HMI-MI: MULTIMODAL INTERACTIONS, IR-75977",

author = "Brais Martinez and Xavier Binefa and Maja Pantic",

note = "10.1109/CVPRW.2010.5543605 ; null ; Conference date: 13-06-2010 Through 18-06-2010",

year = "2010",

month = jun,

day = "14",

doi = "10.1109/CVPRW.2010.5543605",

language = "Undefined",

isbn = "978-1-4244-7029-7",

publisher = "IEEE",

pages = "48--54",

booktitle = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2010, Workshop on Object Tracking & Classification Beyond and in the Visible Spectrum",

}

Martinez, B, Binefa, X & Pantic, M 2010, Facial Component Detection in Thermal Imagery. in IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2010, Workshop on Object Tracking & Classification Beyond and in the Visible Spectrum. IEEE, USA, pp. 48-54, 23rd IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2010, San Francisco, California, United States, 13/06/10. https://doi.org/10.1109/CVPRW.2010.5543605

Facial Component Detection in Thermal Imagery. / Martinez, Brais; Binefa, Xavier; Pantic, Maja.

IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2010, Workshop on Object Tracking & Classification Beyond and in the Visible Spectrum. USA : IEEE, 2010. p. 48-54.

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

TY - GEN

T1 - Facial Component Detection in Thermal Imagery

AU - Martinez, Brais

AU - Binefa, Xavier

AU - Pantic, Maja

N1 - Conference code: 23

PY - 2010/6/14

Y1 - 2010/6/14

N2 - This paper studies the problem of detecting facial components in thermal imagery (specifically eyes, nostrils and mouth). One of the immediate goals is to enable the automatic registration of facial thermal images. The detection of eyes and nostrils is performed using Haar features and the GentleBoost algorithm, which are shown to provide superior detection rates. The detection of the mouth is based on the detections of the eyes and the nostrils and is performed using measures of entropy and self similarity. The results show that reliable facial component detection is feasible using this methodology, getting a correct detection rate for both eyes and nostrils of 0.8. A correct eyes and nostrils detection enables a correct detection of the mouth in 65% of closed-mouth test images and in 73% of open-mouth test images.

AB - This paper studies the problem of detecting facial components in thermal imagery (specifically eyes, nostrils and mouth). One of the immediate goals is to enable the automatic registration of facial thermal images. The detection of eyes and nostrils is performed using Haar features and the GentleBoost algorithm, which are shown to provide superior detection rates. The detection of the mouth is based on the detections of the eyes and the nostrils and is performed using measures of entropy and self similarity. The results show that reliable facial component detection is feasible using this methodology, getting a correct detection rate for both eyes and nostrils of 0.8. A correct eyes and nostrils detection enables a correct detection of the mouth in 65% of closed-mouth test images and in 73% of open-mouth test images.

KW - METIS-276369

KW - EWI-19562

KW - HMI-MI: MULTIMODAL INTERACTIONS

KW - IR-75977

U2 - 10.1109/CVPRW.2010.5543605

DO - 10.1109/CVPRW.2010.5543605

M3 - Conference contribution

SN - 978-1-4244-7029-7

SP - 48

EP - 54

BT - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2010, Workshop on Object Tracking & Classification Beyond and in the Visible Spectrum

PB - IEEE

CY - USA

Y2 - 13 June 2010 through 18 June 2010

ER -