An RGB-D Database Using Microsoft’s Kinect for Windows for Face Detection

Rasmus Idskou Høg, Petr Jasek, Clement Rofidal, Kamal Nasrollahi, Thomas B. Moeslund, Gabrielle Tranchet

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

52 Citations (Scopus)
2759 Downloads (Pure)

Abstract

The very first step in many facial analysis systems is face detection. Though face detection has been studied for many years, there is not still a benchmark public database to be widely accepted among researchers for which both color and depth information are obtained by the same sensor. Most of the available 3d databases have already automatically or manually detected the face images and they are therefore mostly used for face recognition not detection. This paper purposes an RGB-D database containing 1581 images (and their depth counterparts) taken from 31 persons in 17 different poses and facial expressions using a Kinect device. The faces in the images are not extracted neither in the RGB images nor in the depth hereof, therefore they can be used for both detection and recognition. The proposed database has been used in a face detection algorithm which is based on the depth information of the images. The challenges and merits of the database have been highlighted through experimental results.
Original languageEnglish
Title of host publicationIEEE 8th International Conference on Signal Image Technology & Internet Based Systems
Number of pages5
Place of PublicationItaly
PublisherIEEE Computer Society Press
Publication dateNov 2012
Pages42-46
ISBN (Print)978-1-4673-5152-2
DOIs
Publication statusPublished - Nov 2012
EventSignal Image Technology and Internet Based Systems (SITIS), 2012 Eighth International Conference on - Naples, Italy
Duration: 25 Nov 201229 Nov 2012

Conference

ConferenceSignal Image Technology and Internet Based Systems (SITIS), 2012 Eighth International Conference on
CountryItaly
CityNaples
Period25/11/201229/11/2012

Fingerprint

Face recognition
Color
Sensors

Cite this

Idskou Høg, R., Jasek, P., Rofidal, C., Nasrollahi, K., Moeslund, T. B., & Tranchet, G. (2012). An RGB-D Database Using Microsoft’s Kinect for Windows for Face Detection. In IEEE 8th International Conference on Signal Image Technology & Internet Based Systems (pp. 42-46). Italy: IEEE Computer Society Press. https://doi.org/10.1109/SITIS.2012.17
Idskou Høg, Rasmus ; Jasek, Petr ; Rofidal, Clement ; Nasrollahi, Kamal ; Moeslund, Thomas B. ; Tranchet, Gabrielle. / An RGB-D Database Using Microsoft’s Kinect for Windows for Face Detection. IEEE 8th International Conference on Signal Image Technology & Internet Based Systems. Italy : IEEE Computer Society Press, 2012. pp. 42-46
@inproceedings{91d7ad644f054f8cba59f2a411fe01dd,
title = "An RGB-D Database Using Microsoft’s Kinect for Windows for Face Detection",
abstract = "The very first step in many facial analysis systems is face detection. Though face detection has been studied for many years, there is not still a benchmark public database to be widely accepted among researchers for which both color and depth information are obtained by the same sensor. Most of the available 3d databases have already automatically or manually detected the face images and they are therefore mostly used for face recognition not detection. This paper purposes an RGB-D database containing 1581 images (and their depth counterparts) taken from 31 persons in 17 different poses and facial expressions using a Kinect device. The faces in the images are not extracted neither in the RGB images nor in the depth hereof, therefore they can be used for both detection and recognition. The proposed database has been used in a face detection algorithm which is based on the depth information of the images. The challenges and merits of the database have been highlighted through experimental results.",
author = "{Idskou H{\o}g}, Rasmus and Petr Jasek and Clement Rofidal and Kamal Nasrollahi and Moeslund, {Thomas B.} and Gabrielle Tranchet",
year = "2012",
month = "11",
doi = "10.1109/SITIS.2012.17",
language = "English",
isbn = "978-1-4673-5152-2",
pages = "42--46",
booktitle = "IEEE 8th International Conference on Signal Image Technology & Internet Based Systems",
publisher = "IEEE Computer Society Press",
address = "United States",

}

Idskou Høg, R, Jasek, P, Rofidal, C, Nasrollahi, K, Moeslund, TB & Tranchet, G 2012, An RGB-D Database Using Microsoft’s Kinect for Windows for Face Detection. in IEEE 8th International Conference on Signal Image Technology & Internet Based Systems. IEEE Computer Society Press, Italy, pp. 42-46, Signal Image Technology and Internet Based Systems (SITIS), 2012 Eighth International Conference on, Naples, Italy, 25/11/2012. https://doi.org/10.1109/SITIS.2012.17

An RGB-D Database Using Microsoft’s Kinect for Windows for Face Detection. / Idskou Høg, Rasmus; Jasek, Petr; Rofidal, Clement; Nasrollahi, Kamal; Moeslund, Thomas B.; Tranchet, Gabrielle.

IEEE 8th International Conference on Signal Image Technology & Internet Based Systems. Italy : IEEE Computer Society Press, 2012. p. 42-46.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - An RGB-D Database Using Microsoft’s Kinect for Windows for Face Detection

AU - Idskou Høg, Rasmus

AU - Jasek, Petr

AU - Rofidal, Clement

AU - Nasrollahi, Kamal

AU - Moeslund, Thomas B.

AU - Tranchet, Gabrielle

PY - 2012/11

Y1 - 2012/11

N2 - The very first step in many facial analysis systems is face detection. Though face detection has been studied for many years, there is not still a benchmark public database to be widely accepted among researchers for which both color and depth information are obtained by the same sensor. Most of the available 3d databases have already automatically or manually detected the face images and they are therefore mostly used for face recognition not detection. This paper purposes an RGB-D database containing 1581 images (and their depth counterparts) taken from 31 persons in 17 different poses and facial expressions using a Kinect device. The faces in the images are not extracted neither in the RGB images nor in the depth hereof, therefore they can be used for both detection and recognition. The proposed database has been used in a face detection algorithm which is based on the depth information of the images. The challenges and merits of the database have been highlighted through experimental results.

AB - The very first step in many facial analysis systems is face detection. Though face detection has been studied for many years, there is not still a benchmark public database to be widely accepted among researchers for which both color and depth information are obtained by the same sensor. Most of the available 3d databases have already automatically or manually detected the face images and they are therefore mostly used for face recognition not detection. This paper purposes an RGB-D database containing 1581 images (and their depth counterparts) taken from 31 persons in 17 different poses and facial expressions using a Kinect device. The faces in the images are not extracted neither in the RGB images nor in the depth hereof, therefore they can be used for both detection and recognition. The proposed database has been used in a face detection algorithm which is based on the depth information of the images. The challenges and merits of the database have been highlighted through experimental results.

UR - http://www.scopus.com/inward/record.url?scp=84874030656&partnerID=8YFLogxK

U2 - 10.1109/SITIS.2012.17

DO - 10.1109/SITIS.2012.17

M3 - Article in proceeding

SN - 978-1-4673-5152-2

SP - 42

EP - 46

BT - IEEE 8th International Conference on Signal Image Technology & Internet Based Systems

PB - IEEE Computer Society Press

CY - Italy

ER -

Idskou Høg R, Jasek P, Rofidal C, Nasrollahi K, Moeslund TB, Tranchet G. An RGB-D Database Using Microsoft’s Kinect for Windows for Face Detection. In IEEE 8th International Conference on Signal Image Technology & Internet Based Systems. Italy: IEEE Computer Society Press. 2012. p. 42-46 https://doi.org/10.1109/SITIS.2012.17