Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Prosopagnosia01:24

Prosopagnosia

247
Prosopagnosia, also known as face blindness, is the inability to recognize faces. In severe cases, individuals with prosopagnosia may not recognize close family members, including parents and spouses, by their faces. For instance, someone with prosopagnosia might walk past their child in a crowd, only realizing their mistake upon noticing their child's distinctive backpack or favorite jacket. Prosopagnosia specifically impairs facial recognition, while the recognition of other objects or...
247
Visual Agnosia01:12

Visual Agnosia

286
Visual agnosia is a condition characterized by the inability to recognize visually presented objects despite having normal vision. For instance, a person with visual agnosia can describe the shape and color of an object but cannot identify or name it. This impairment does not affect their visual field, acuity, color vision, brightness discrimination, language, or memory. An example of this condition in a social setting is someone at a dinner party asking for "that silver thing with a round...
286

You might also read

Related Articles

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

Sort by
Same author

An Ultrasonic-Based Sensor System for Elderly Fall Monitoring in a Smart Room.

Journal of healthcare engineering·2022
Same author

Emotion Recognition for Partial Faces Using a Feature Vector Technique.

Sensors (Basel, Switzerland)·2022
Same author

American Sign Language Words Recognition of Skeletal Videos Using Processed Video Driven Multi-Stacked Deep LSTM.

Sensors (Basel, Switzerland)·2022
Same author

Initial Geometrical Templates with Parameter Sets for Active Contour on Skin Cancer Boundary Segmentation.

Journal of healthcare engineering·2021
Same author

Semi-automatic liver segmentation based on probabilistic models and anatomical constraints.

Scientific reports·2021

Related Experiment Video

Updated: Sep 6, 2025

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication
07:18

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication

Published on: January 26, 2024

963

Backhand-Approach-Based American Sign Language Words Recognition Using Spatial-Temporal Body Parts and Hand

Ponlawat Chophuk1, Kosin Chamnongthai1, Krisana Chinnasarn2

  • 1Department of Electronic and Telecommunication Engineering, Faculty of Engineering, King Mongkut's University of Technology Thonburi, Bangkok 10140, Thailand.

Sensors (Basel, Switzerland)
|June 24, 2022
PubMed
Summary

This study introduces novel feature models for American Sign Language (ASL) recognition, significantly improving accuracy by analyzing hand-body and hand-hand relationships. The new method achieves high performance in recognizing ASL letters and words.

Keywords:
American sign language wordsSRM sign groupbackhand approachbidirectional long short-term memory (BiLSTM)computer visionleap motion sensorportable systemthe spatial–temporal body parts and hand relationship patterns (ST-BHR patterns)video processing

More Related Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.1K
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.7K

Related Experiment Videos

Last Updated: Sep 6, 2025

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication
07:18

Author Spotlight: Deciphering the Cognitive and Neural Mechanisms of Gesture in Communication

Published on: January 26, 2024

963
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

4.1K
Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

1.7K

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Human-Computer Interaction

Background:

  • Existing sign language recognition methods often overlook crucial hand-body and hand-hand relationships, limiting their ability to distinguish similar signs.
  • The backhand approach in sign recognition requires detailed analysis of spatial-temporal dynamics and inter-part relationships.

Purpose of the Study:

  • To propose and evaluate novel feature-based models for enhanced American Sign Language (ASL) recognition.
  • To address the limitations of existing methods by incorporating spatial-temporal body part and hand relationships.

Main Methods:

  • Developed four feature models: spatial-temporal body parts and hand relationships, finger joint angles, 3D hand motion trajectories, and double-hand relationships.
  • Employed a two-layer bidirectional long short-term memory (LSTM) network as a classifier for time-independent data.

Main Results:

  • Achieved 97.34% accuracy and 97.36% F1-score on 26 ASL letters.
  • Attained 98.52% accuracy and 98.54% F1-score on 40 double-hand ASL words.
  • Demonstrated superior performance compared to existing methods, with approximately 96.99% accuracy and 97.00% F1-score on 72 new ASL words from 10 participants.

Conclusions:

  • The proposed feature models and LSTM classifier significantly outperform existing approaches in ASL recognition.
  • Incorporating spatial-temporal relationships between hands and body parts is key to improving the accuracy of recognizing similar ASL signs.