Automatic Extraction of Lip Feature Points

Roland GOECKE, J. Bruce Millar, Alexander Zelinsky, Jordi Robert-Ribes

Research output: A Conference proceeding or a Chapter in BookConference contribution

Abstract

We present a novyl algorithm for the robust and reliable automatic extraction of lip featu;re points for speechreading. The algorithm uses a combination of colour information in the im- age data and knowledge about the structure of the mouth area to find certain feature points on the inner lip contour. A new confidence mea- sure quantifying how well the feature extraction process worked is introduced. A parameter set describing the shape of the mouth is. derived from the positions of the feature points. Using a stereo camera system, measurements are in 3D. Such a 3D parameter set is of great value for automatic speech-reading systems.
Original languageEnglish
Title of host publicationProceedings of the Australian Conference on Robotics and Automation ACRA 2000
Place of PublicationMelbourne
PublisherAustralian Robotics & Automation Association
Pages31-36
Number of pages6
ISBN (Print)0732621410
Publication statusPublished - 30 Aug 2000
EventAustralian Conference on Robotics and Automation ACRA 2000 - Melbourne, Australia
Duration: 30 Aug 20001 Sep 2000

Conference

ConferenceAustralian Conference on Robotics and Automation ACRA 2000
Abbreviated titleACRA 2000
CountryAustralia
CityMelbourne
Period30/08/001/09/00

Fingerprint

parameter
speech

Cite this

GOECKE, R., Millar, J. B., Zelinsky, A., & Robert-Ribes, J. (2000). Automatic Extraction of Lip Feature Points. In Proceedings of the Australian Conference on Robotics and Automation ACRA 2000 (pp. 31-36). Melbourne: Australian Robotics & Automation Association.
GOECKE, Roland ; Millar, J. Bruce ; Zelinsky, Alexander ; Robert-Ribes, Jordi. / Automatic Extraction of Lip Feature Points. Proceedings of the Australian Conference on Robotics and Automation ACRA 2000. Melbourne : Australian Robotics & Automation Association, 2000. pp. 31-36
@inproceedings{cf66de9cb07b4208b1d74b763d8a3a99,
title = "Automatic Extraction of Lip Feature Points",
abstract = "We present a novyl algorithm for the robust and reliable automatic extraction of lip featu;re points for speechreading. The algorithm uses a combination of colour information in the im- age data and knowledge about the structure of the mouth area to find certain feature points on the inner lip contour. A new confidence mea- sure quantifying how well the feature extraction process worked is introduced. A parameter set describing the shape of the mouth is. derived from the positions of the feature points. Using a stereo camera system, measurements are in 3D. Such a 3D parameter set is of great value for automatic speech-reading systems.",
keywords = "Lip tracking",
author = "Roland GOECKE and Millar, {J. Bruce} and Alexander Zelinsky and Jordi Robert-Ribes",
year = "2000",
month = "8",
day = "30",
language = "English",
isbn = "0732621410",
pages = "31--36",
booktitle = "Proceedings of the Australian Conference on Robotics and Automation ACRA 2000",
publisher = "Australian Robotics & Automation Association",

}

GOECKE, R, Millar, JB, Zelinsky, A & Robert-Ribes, J 2000, Automatic Extraction of Lip Feature Points. in Proceedings of the Australian Conference on Robotics and Automation ACRA 2000. Australian Robotics & Automation Association, Melbourne, pp. 31-36, Australian Conference on Robotics and Automation ACRA 2000, Melbourne, Australia, 30/08/00.

Automatic Extraction of Lip Feature Points. / GOECKE, Roland; Millar, J. Bruce; Zelinsky, Alexander; Robert-Ribes, Jordi.

Proceedings of the Australian Conference on Robotics and Automation ACRA 2000. Melbourne : Australian Robotics & Automation Association, 2000. p. 31-36.

Research output: A Conference proceeding or a Chapter in BookConference contribution

TY - GEN

T1 - Automatic Extraction of Lip Feature Points

AU - GOECKE, Roland

AU - Millar, J. Bruce

AU - Zelinsky, Alexander

AU - Robert-Ribes, Jordi

PY - 2000/8/30

Y1 - 2000/8/30

N2 - We present a novyl algorithm for the robust and reliable automatic extraction of lip featu;re points for speechreading. The algorithm uses a combination of colour information in the im- age data and knowledge about the structure of the mouth area to find certain feature points on the inner lip contour. A new confidence mea- sure quantifying how well the feature extraction process worked is introduced. A parameter set describing the shape of the mouth is. derived from the positions of the feature points. Using a stereo camera system, measurements are in 3D. Such a 3D parameter set is of great value for automatic speech-reading systems.

AB - We present a novyl algorithm for the robust and reliable automatic extraction of lip featu;re points for speechreading. The algorithm uses a combination of colour information in the im- age data and knowledge about the structure of the mouth area to find certain feature points on the inner lip contour. A new confidence mea- sure quantifying how well the feature extraction process worked is introduced. A parameter set describing the shape of the mouth is. derived from the positions of the feature points. Using a stereo camera system, measurements are in 3D. Such a 3D parameter set is of great value for automatic speech-reading systems.

KW - Lip tracking

M3 - Conference contribution

SN - 0732621410

SP - 31

EP - 36

BT - Proceedings of the Australian Conference on Robotics and Automation ACRA 2000

PB - Australian Robotics & Automation Association

CY - Melbourne

ER -

GOECKE R, Millar JB, Zelinsky A, Robert-Ribes J. Automatic Extraction of Lip Feature Points. In Proceedings of the Australian Conference on Robotics and Automation ACRA 2000. Melbourne: Australian Robotics & Automation Association. 2000. p. 31-36