Movement epenthesis generation using NURBS-based spatial interpolation

Ze Jing Chuang, Chung-Hsien Wu, Wei Sheng Chen

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

This study proposes a novel approach to the generation of video-based movement epenthesis for sign language and concentrates on a spatial interpolation approach using a nonuniform rational B-spline 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. The distance cost is defined as the normalized Euclidian distance between the palm locations at two cut points. The smoothness cost is determined by accumulating the second derivative of the curve. The image distortion cost is then estimated from the normalized Euclidian distance between the real and generated hand images. To evaluate the proposed approach, a set of sign video databases is collected and preprocessed with image calibration, content annotation, and principle component analysis. An image component overlapping procedure is also employed to yield a smooth sign video output. Evaluation results demonstrate that the synthesized trajectory is very close to the original trajectory. Moreover, the system was evaluated subjectively based on the results often hearing and five deaf people. The evaluation results also demonstrate the stability and feasibility of the proposed approach.

Original languageEnglish
Pages (from-to)1313-1323
Number of pages11
JournalIEEE Transactions on Circuits and Systems for Video Technology
Volume16
Issue number11
DOIs
Publication statusPublished - 2006 Nov 1

Fingerprint

Interpolation
Costs
Trajectories
Audition
Splines
Calibration
Derivatives

All Science Journal Classification (ASJC) codes

  • Media Technology
  • Electrical and Electronic Engineering

Cite this

@article{de0675c458ff40688f4a3a3e840eaeaf,
title = "Movement epenthesis generation using NURBS-based spatial interpolation",
abstract = "This study proposes a novel approach to the generation of video-based movement epenthesis for sign language and concentrates on a spatial interpolation approach using a nonuniform rational B-spline 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. The distance cost is defined as the normalized Euclidian distance between the palm locations at two cut points. The smoothness cost is determined by accumulating the second derivative of the curve. The image distortion cost is then estimated from the normalized Euclidian distance between the real and generated hand images. To evaluate the proposed approach, a set of sign video databases is collected and preprocessed with image calibration, content annotation, and principle component analysis. An image component overlapping procedure is also employed to yield a smooth sign video output. Evaluation results demonstrate that the synthesized trajectory is very close to the original trajectory. Moreover, the system was evaluated subjectively based on the results often hearing and five deaf people. The evaluation results also demonstrate the stability and feasibility of the proposed approach.",
author = "Chuang, {Ze Jing} and Chung-Hsien Wu and Chen, {Wei Sheng}",
year = "2006",
month = "11",
day = "1",
doi = "10.1109/TCSVT.2006.883509",
language = "English",
volume = "16",
pages = "1313--1323",
journal = "IEEE Transactions on Circuits and Systems for Video Technology",
issn = "1051-8215",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

Movement epenthesis generation using NURBS-based spatial interpolation. / Chuang, Ze Jing; Wu, Chung-Hsien; Chen, Wei Sheng.

In: IEEE Transactions on Circuits and Systems for Video Technology, Vol. 16, No. 11, 01.11.2006, p. 1313-1323.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Movement epenthesis generation using NURBS-based spatial interpolation

AU - Chuang, Ze Jing

AU - Wu, Chung-Hsien

AU - Chen, Wei Sheng

PY - 2006/11/1

Y1 - 2006/11/1

N2 - This study proposes a novel approach to the generation of video-based movement epenthesis for sign language and concentrates on a spatial interpolation approach using a nonuniform rational B-spline 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. The distance cost is defined as the normalized Euclidian distance between the palm locations at two cut points. The smoothness cost is determined by accumulating the second derivative of the curve. The image distortion cost is then estimated from the normalized Euclidian distance between the real and generated hand images. To evaluate the proposed approach, a set of sign video databases is collected and preprocessed with image calibration, content annotation, and principle component analysis. An image component overlapping procedure is also employed to yield a smooth sign video output. Evaluation results demonstrate that the synthesized trajectory is very close to the original trajectory. Moreover, the system was evaluated subjectively based on the results often hearing and five deaf people. The evaluation results also demonstrate the stability and feasibility of the proposed approach.

AB - This study proposes a novel approach to the generation of video-based movement epenthesis for sign language and concentrates on a spatial interpolation approach using a nonuniform rational B-spline 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. The distance cost is defined as the normalized Euclidian distance between the palm locations at two cut points. The smoothness cost is determined by accumulating the second derivative of the curve. The image distortion cost is then estimated from the normalized Euclidian distance between the real and generated hand images. To evaluate the proposed approach, a set of sign video databases is collected and preprocessed with image calibration, content annotation, and principle component analysis. An image component overlapping procedure is also employed to yield a smooth sign video output. Evaluation results demonstrate that the synthesized trajectory is very close to the original trajectory. Moreover, the system was evaluated subjectively based on the results often hearing and five deaf people. The evaluation results also demonstrate the stability and feasibility of the proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=33751528242&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33751528242&partnerID=8YFLogxK

U2 - 10.1109/TCSVT.2006.883509

DO - 10.1109/TCSVT.2006.883509

M3 - Article

VL - 16

SP - 1313

EP - 1323

JO - IEEE Transactions on Circuits and Systems for Video Technology

JF - IEEE Transactions on Circuits and Systems for Video Technology

SN - 1051-8215

IS - 11

ER -