Movement epenthesis generation for sign language synthesis using NURBS function

Ze Jing Chuang, Chung Hsien Wu, Wei Sheng Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This study proposes an approach to the generation of video-based movement epenthesis for sign language, and concentrates on a spatial interpolation approach using a Non-Uniform Rational B-spline (NURBS) function to produce a smooth interpolation curve. To generate movement epenthesis, the beginning and end "cut points" are determined based on the concatenation cost, which is a linear combination of the distance, smoothness and image distortion costs. An image component overlapping procedure is also employed to yield a smooth sign video output. To evaluate the proposed approach, a set of sign video databases is collected and preprocessed with image calibration, content annotation and principle component analysis (PCA). Evaluation results demonstrate that the synthesized trajectory is very close to the original trajectory. Moreover, The evaluation results also demonstrate the stability and feasibility of the proposed approach.

Original languageEnglish
Title of host publication2006 IEEE Region 10 Conference, TENCON 2006
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Print)1424405491, 9781424405497
DOIs
Publication statusPublished - 2006 Jan 1
Event2006 IEEE Region 10 Conference, TENCON 2006 - Hong Kong, China
Duration: 2006 Nov 142006 Nov 17

Publication series

NameIEEE Region 10 Annual International Conference, Proceedings/TENCON
ISSN (Print)2159-3442
ISSN (Electronic)2159-3450

Other

Other2006 IEEE Region 10 Conference, TENCON 2006
CountryChina
CityHong Kong
Period06-11-1406-11-17

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Movement epenthesis generation for sign language synthesis using NURBS function'. Together they form a unique fingerprint.

Cite this