Image sequence analysis using a spatio-temporal coding for automatic lipreading

Author

Baig, Abdul Rauf ; Séguier, Renaud ; Vaucher, Gilles

Author_Institution

Signal Process. & Neural Networks Team, Supelec, Cesson Sevigne, France

fYear

1999

fDate

1999

Firstpage

544

Lastpage

549

Abstract

In this paper we present the details of a processing technique utilised to extract parameters from the images of a talking person´s mouth region. These parameters are converted into impulse sequences for a given series of images. Spatio-temporal (ST) coding of the impulses provide an input to a spatio-temporal neural network architecture. The system is tested on a French digit recognition task and the results obtained are given. The overall procedure is sufficiently simple to allow us to make plans for its realisation as a real-time system

Keywords

face recognition; feature extraction; image coding; image sequences; neural net architecture; parameter estimation; real-time systems; speech recognition; French digit; automatic lipreading; digit recognition task; image sequence analysis; image series; impulse sequences; neural network architecture; parameter extraction; real-time system; spatio-temporal coding; Cameras; Color; Crosstalk; Hydrogen; Image coding; Image sequence analysis; Lips; Mouth; Neural networks; Speech recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis and Processing, 1999. Proceedings. International Conference on

Conference_Location

Venice

Print_ISBN

0-7695-0040-4

Type

conf

DOI

10.1109/ICIAP.1999.797652

Filename

797652