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.
Image sequence analysis using a spatio-temporal coding for automatic lipreading
1999-01-01
163159 byte
Conference paper
Electronic Resource
English
Image Sequence Analysis using a Spatio-Temporal Coding for Automatic Lipreading
British Library Conference Proceedings | 1999
|Measurement of traffic parameters in image sequence using spatio-temporal information
Tema Archive | 2008
|Effectiveness Evaluation of Word Characteristics Obtained from 3-D Image Information for Lipreading
British Library Conference Proceedings | 2001
|