Intelligent temporal subsampling of American sign language using event boundaries

Video sequences of ASL were investigated in 2 modes: ordinary video and frames printed side by side on the display. An activity index was used to choose critical frames at event boundaries, times when the difference between successive frames is at a local minimum. Sign intelligibility was measured f...

Full description

Saved in:
Bibliographic Details
Published in:Journal of experimental psychology. Human perception and performance 1990-05, Vol.16 (May 90), p.282-294
Main Authors: Parish, D H, Sperling, G, Landy, M S
Format: Article
Language:English
Subjects:
American sign language
Readability
Time sampling
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Video sequences of ASL were investigated in 2 modes: ordinary video and frames printed side by side on the display. An activity index was used to choose critical frames at event boundaries, times when the difference between successive frames is at a local minimum. Sign intelligibility was measured for 32 experienced ASL signers who viewed individual signs. Concludes that event boundaries can be defined computationaly and that subsampling from event boundaries is better than choosing at regular intervals. (Abstract amended)
ISSN:0096-1523