ICIP 2006, Atlanta, GA
 
ICIP 2006 Home
Organizing Committee
Call for Papers
Technical Program
Meeting Schedule
Plenaries
Special Sessions
Tutorials
MathWorks Seminar
Paper Submission
Paper Awards
Registration
Supporters
Exhibits
Loans
Venue
Local Information
Debt Consolidation
Discussion Forum
Contact Us

Slide Show

Atlanta Conv. & Vis. Bureau
 

Technical Program

Paper Detail

Paper:WA-P8.4
Session:Image/Video Processing Applications: Object Detection and Recognition
Time:Wednesday, October 11, 09:40 - 12:20
Presentation: Poster
Title: DYNAMIC FINGERSPELLING RECOGNITION USING GEOMETRIC AND MOTION FEATURES
Authors: Paul Goh; Unversity of Western Australia 
 Eun-Jung Holden; Unversity of Western Australia 
Abstract: This paper presents the Australian sign language (Auslan) Fingerspelling Recognizer (AFR): a system capable of recognizing signs consisting of Auslan manual alphabet letters from video sequences. The AFR system uses a combination of geometric features and motion feature based on optical flow which are extracted from video sequences. The sequence of features are then classified using Hidden Markov Models. Tests using a vocabulary of twenty signed words showed the system could achieve 97% accuracy at the letter level and 88% at the word level by using a finite state grammar network and embedded training.
IEEE Signal Processing Society

Last Updated: Friday, July 21, 2006 10:32:01 AM
For comments and questions regarding this Web site, contact Memphis Web Design.