Video-based Side-view Face Recognition for Home Safety

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

16 Downloads (Pure)

Abstract

In this paper, we introduce a registration method for side-view face recognition that is suitable for home safety applications. We use cameras attached at door posts, and recognize people as they pass through doors to estimate their location in the house. First, we present a new database that is collected using this setup, where we use side cameras and ambient light. We recorded videos of 14 people that pass through doors in 18 different paths. Next, we propose our recognition method where we automatically find the profile to register the face images. By applying hierarchical clustering we detect the frames that include falsely detected profiles and pose variations, and automatically remove them from the video sequence to improve our results. After registering, we find the nose tip, apply recognition based on profiles, and analyze our results.
Original languageEnglish
Title of host publication33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux
Place of PublicationEnschede
PublisherWerkgemeenschap voor Informatie- en Communicatietheorie (WIC)
Pages220-227
Number of pages8
ISBN (Print)978-90-365-3383-6
Publication statusPublished - May 2012
Event33rd WIC Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux 2012 - Boekelo, Netherlands
Duration: 24 May 201225 May 2012
Conference number: 33

Conference

Conference33rd WIC Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux 2012
CountryNetherlands
CityBoekelo
Period24/05/1225/05/12

Fingerprint

Face recognition
Cameras

Keywords

  • SCS-Safety
  • IR-84167
  • METIS-296303
  • EWI-23079

Cite this

Santemiz, P., Spreeuwers, L. J., & Veldhuis, R. N. J. (2012). Video-based Side-view Face Recognition for Home Safety. In 33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux (pp. 220-227). Enschede: Werkgemeenschap voor Informatie- en Communicatietheorie (WIC).
Santemiz, Pinar ; Spreeuwers, Luuk J. ; Veldhuis, Raymond N.J. / Video-based Side-view Face Recognition for Home Safety. 33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux. Enschede : Werkgemeenschap voor Informatie- en Communicatietheorie (WIC), 2012. pp. 220-227
@inproceedings{242227c3507b4ac6a932af112eb62fbd,
title = "Video-based Side-view Face Recognition for Home Safety",
abstract = "In this paper, we introduce a registration method for side-view face recognition that is suitable for home safety applications. We use cameras attached at door posts, and recognize people as they pass through doors to estimate their location in the house. First, we present a new database that is collected using this setup, where we use side cameras and ambient light. We recorded videos of 14 people that pass through doors in 18 different paths. Next, we propose our recognition method where we automatically find the profile to register the face images. By applying hierarchical clustering we detect the frames that include falsely detected profiles and pose variations, and automatically remove them from the video sequence to improve our results. After registering, we find the nose tip, apply recognition based on profiles, and analyze our results.",
keywords = "SCS-Safety, IR-84167, METIS-296303, EWI-23079",
author = "Pinar Santemiz and Spreeuwers, {Luuk J.} and Veldhuis, {Raymond N.J.}",
year = "2012",
month = "5",
language = "English",
isbn = "978-90-365-3383-6",
pages = "220--227",
booktitle = "33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux",
publisher = "Werkgemeenschap voor Informatie- en Communicatietheorie (WIC)",
address = "Netherlands",

}

Santemiz, P, Spreeuwers, LJ & Veldhuis, RNJ 2012, Video-based Side-view Face Recognition for Home Safety. in 33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux. Werkgemeenschap voor Informatie- en Communicatietheorie (WIC), Enschede, pp. 220-227, 33rd WIC Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux 2012, Boekelo, Netherlands, 24/05/12.

Video-based Side-view Face Recognition for Home Safety. / Santemiz, Pinar; Spreeuwers, Luuk J.; Veldhuis, Raymond N.J.

33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux. Enschede : Werkgemeenschap voor Informatie- en Communicatietheorie (WIC), 2012. p. 220-227.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademic

TY - GEN

T1 - Video-based Side-view Face Recognition for Home Safety

AU - Santemiz, Pinar

AU - Spreeuwers, Luuk J.

AU - Veldhuis, Raymond N.J.

PY - 2012/5

Y1 - 2012/5

N2 - In this paper, we introduce a registration method for side-view face recognition that is suitable for home safety applications. We use cameras attached at door posts, and recognize people as they pass through doors to estimate their location in the house. First, we present a new database that is collected using this setup, where we use side cameras and ambient light. We recorded videos of 14 people that pass through doors in 18 different paths. Next, we propose our recognition method where we automatically find the profile to register the face images. By applying hierarchical clustering we detect the frames that include falsely detected profiles and pose variations, and automatically remove them from the video sequence to improve our results. After registering, we find the nose tip, apply recognition based on profiles, and analyze our results.

AB - In this paper, we introduce a registration method for side-view face recognition that is suitable for home safety applications. We use cameras attached at door posts, and recognize people as they pass through doors to estimate their location in the house. First, we present a new database that is collected using this setup, where we use side cameras and ambient light. We recorded videos of 14 people that pass through doors in 18 different paths. Next, we propose our recognition method where we automatically find the profile to register the face images. By applying hierarchical clustering we detect the frames that include falsely detected profiles and pose variations, and automatically remove them from the video sequence to improve our results. After registering, we find the nose tip, apply recognition based on profiles, and analyze our results.

KW - SCS-Safety

KW - IR-84167

KW - METIS-296303

KW - EWI-23079

M3 - Conference contribution

SN - 978-90-365-3383-6

SP - 220

EP - 227

BT - 33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux

PB - Werkgemeenschap voor Informatie- en Communicatietheorie (WIC)

CY - Enschede

ER -

Santemiz P, Spreeuwers LJ, Veldhuis RNJ. Video-based Side-view Face Recognition for Home Safety. In 33rd Symposium on Information Theory in the Benelux and the 2nd Joint WIC/IEEE Symposium on Information Theory and Signal Processing in the Benelux. Enschede: Werkgemeenschap voor Informatie- en Communicatietheorie (WIC). 2012. p. 220-227