Face detection on AIBO by using the RBF and particle filtering

Kohki Abiko, Taiki Fuji, Hironobu Fukai, Yasue Mitsukura

Research output: Contribution to journalArticle

Abstract

We propose a face-tracking system for AIBO by using skin colors. If AIBO finds a face, AIBO can acquire a condition of user and act more actively. In this paper, we focus on the human-face, which has many kinds of characteristic parts in a human (i.e. age, gender, expression). We detect a face using the radial basis function (RBF) network and the particle filter. First, we use the RBF network for the purpose of skin color recognition. Second, we use the particle filter in order to detect a face in the skin color area, based on the motion pattern of a face. Moreover, in order to show the effectiveness of the proposed method, we perform computer simulations. In various light conditions, we have relatively good results of the skin color recognition. Furthermore, we show a possibility of little false recognitions in unknown color, using the RBF network. Moreover, by applying moving images to the particle filters, we detect and track the face in various noisy environments. Finally, we achieve the face tracking system for AIBO in a real system. It will be shown that AIBO can detect and track the face.

Original languageEnglish
Pages (from-to)3411-3422
Number of pages12
JournalInformation
Volume15
Issue number8
Publication statusPublished - 2012 Aug
Externally publishedYes

Fingerprint

Face recognition
Radial basis function networks
Color
Skin
Computer simulation

ASJC Scopus subject areas

  • General

Cite this

Abiko, K., Fuji, T., Fukai, H., & Mitsukura, Y. (2012). Face detection on AIBO by using the RBF and particle filtering. Information, 15(8), 3411-3422.

Face detection on AIBO by using the RBF and particle filtering. / Abiko, Kohki; Fuji, Taiki; Fukai, Hironobu; Mitsukura, Yasue.

In: Information, Vol. 15, No. 8, 08.2012, p. 3411-3422.

Research output: Contribution to journalArticle

Abiko, K, Fuji, T, Fukai, H & Mitsukura, Y 2012, 'Face detection on AIBO by using the RBF and particle filtering', Information, vol. 15, no. 8, pp. 3411-3422.
Abiko, Kohki ; Fuji, Taiki ; Fukai, Hironobu ; Mitsukura, Yasue. / Face detection on AIBO by using the RBF and particle filtering. In: Information. 2012 ; Vol. 15, No. 8. pp. 3411-3422.
@article{8762f94027e64551989626ff0fc770a1,
title = "Face detection on AIBO by using the RBF and particle filtering",
abstract = "We propose a face-tracking system for AIBO by using skin colors. If AIBO finds a face, AIBO can acquire a condition of user and act more actively. In this paper, we focus on the human-face, which has many kinds of characteristic parts in a human (i.e. age, gender, expression). We detect a face using the radial basis function (RBF) network and the particle filter. First, we use the RBF network for the purpose of skin color recognition. Second, we use the particle filter in order to detect a face in the skin color area, based on the motion pattern of a face. Moreover, in order to show the effectiveness of the proposed method, we perform computer simulations. In various light conditions, we have relatively good results of the skin color recognition. Furthermore, we show a possibility of little false recognitions in unknown color, using the RBF network. Moreover, by applying moving images to the particle filters, we detect and track the face in various noisy environments. Finally, we achieve the face tracking system for AIBO in a real system. It will be shown that AIBO can detect and track the face.",
author = "Kohki Abiko and Taiki Fuji and Hironobu Fukai and Yasue Mitsukura",
year = "2012",
month = "8",
language = "English",
volume = "15",
pages = "3411--3422",
journal = "Information (Japan)",
issn = "1343-4500",
publisher = "International Information Institute",
number = "8",

}

TY - JOUR

T1 - Face detection on AIBO by using the RBF and particle filtering

AU - Abiko, Kohki

AU - Fuji, Taiki

AU - Fukai, Hironobu

AU - Mitsukura, Yasue

PY - 2012/8

Y1 - 2012/8

N2 - We propose a face-tracking system for AIBO by using skin colors. If AIBO finds a face, AIBO can acquire a condition of user and act more actively. In this paper, we focus on the human-face, which has many kinds of characteristic parts in a human (i.e. age, gender, expression). We detect a face using the radial basis function (RBF) network and the particle filter. First, we use the RBF network for the purpose of skin color recognition. Second, we use the particle filter in order to detect a face in the skin color area, based on the motion pattern of a face. Moreover, in order to show the effectiveness of the proposed method, we perform computer simulations. In various light conditions, we have relatively good results of the skin color recognition. Furthermore, we show a possibility of little false recognitions in unknown color, using the RBF network. Moreover, by applying moving images to the particle filters, we detect and track the face in various noisy environments. Finally, we achieve the face tracking system for AIBO in a real system. It will be shown that AIBO can detect and track the face.

AB - We propose a face-tracking system for AIBO by using skin colors. If AIBO finds a face, AIBO can acquire a condition of user and act more actively. In this paper, we focus on the human-face, which has many kinds of characteristic parts in a human (i.e. age, gender, expression). We detect a face using the radial basis function (RBF) network and the particle filter. First, we use the RBF network for the purpose of skin color recognition. Second, we use the particle filter in order to detect a face in the skin color area, based on the motion pattern of a face. Moreover, in order to show the effectiveness of the proposed method, we perform computer simulations. In various light conditions, we have relatively good results of the skin color recognition. Furthermore, we show a possibility of little false recognitions in unknown color, using the RBF network. Moreover, by applying moving images to the particle filters, we detect and track the face in various noisy environments. Finally, we achieve the face tracking system for AIBO in a real system. It will be shown that AIBO can detect and track the face.

UR - http://www.scopus.com/inward/record.url?scp=84864325893&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864325893&partnerID=8YFLogxK

M3 - Article

VL - 15

SP - 3411

EP - 3422

JO - Information (Japan)

JF - Information (Japan)

SN - 1343-4500

IS - 8

ER -