Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 17, 2026

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

Handling movement epenthesis and hand segmentation ambiguities in continuous sign language recognition using nested

Ruiduo Yang¹, Sudeep Sarkar, Barbara Loeding

¹University of South Florida, Tampa, FL, USA. ryang@cse.usf.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence

|January 16, 2010

Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Automated pressure ulcer dimension measurements using a depth camera.

Journal of wound care·2025

Same author

Measuring Human and Economic Activity From Satellite Imagery to Support City-Scale Decision-Making During COVID-19 Pandemic.

IEEE transactions on big data·2023

Same author

Leveraging Symbolic Knowledge Bases for Commonsense Natural Language Inference Using Pattern Theory.

IEEE transactions on pattern analysis and machine intelligence·2023

Same author

Metal-Free <i>S</i>-Arylation of Phosphorothioate Diesters and Related Compounds with Diaryliodonium Salts.

Organic letters·2023

Same author

Non-Boolean computing with nanomagnets for computer vision applications.

Nature nanotechnology·2015

Same author

Hop-Diffusion Monte Carlo for Epipolar Geometry Estimation between Very Wide-Baseline Images.

IEEE transactions on pattern analysis and machine intelligence·2015

This study introduces a new framework for continuous sign language recognition, improving accuracy by addressing movement epenthesis and hand segmentation. The enhanced dynamic programming approach significantly outperforms existing methods.

Area of Science:

Computer Science
Artificial Intelligence
Computational Linguistics

Background:

Continuous sign language recognition faces challenges with movement epenthesis (me) and accurate hand segmentation.
Existing methods like Conditional Random Fields (CRF) struggle with these complexities.

Purpose of the Study:

To develop a robust framework for unaided, continuous sign language recognition.
To effectively handle movement epenthesis and hand segmentation/grouping problems.

Main Methods:

An enhanced, nested dynamic programming (DP) approach called enhanced level building (eLB) was developed.
The eLB algorithm incorporates a virtual 'me' option to model movement epenthesis without explicit models.
A nested DP handles multi-hand candidate selection, integrating grammar models.

More Related Videos

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

Published on: April 3, 2026

Related Experiment Videos

Last Updated: Jun 17, 2026

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English

Published on: April 3, 2026

Main Results:

The eLB algorithm demonstrated over 40% improvement in frame labeling rate compared to CRF and Latent Dynamic-CRF (LDCRF).
Achieved a 70% improvement in sign recognition rate over unenhanced DP algorithms lacking 'me' effect accommodation.
The framework showed flexibility in handling changing contexts and diverse datasets.

Conclusions:

The proposed enhanced DP framework offers a significant advancement in continuous sign language recognition.
It effectively addresses key challenges like movement epenthesis and hand segmentation, leading to higher accuracy.
This approach provides a flexible and powerful tool for sign language processing research.