Related Experiment Video
Updated: Dec 28, 2025
08:15
Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision
Published on: March 28, 2025
1.1K
Real Time Hand Movement Trajectory Tracking for Enhancing Dementia Screening in Ageing Deaf Signers of British Sign
Xing Liang1, Epaminondas Kapetanios1, Bencie Woll2
1Cognitive Computing Research Lab, University of Westminster, London, UK.
IFIP Advances in Information and Communication Technology
|February 19, 2020
Summary
Machine learning tracks British Sign Language (BSL) hand movements for early dementia detection in Deaf individuals. This novel approach analyzes sign trajectories and facial expressions using 2D videos, improving upon existing methods.
Area of Science:
- Computational neuroscience
- Medical imaging analysis
- Machine learning applications
Background:
- Dementia diagnosis in Deaf British Sign Language (BSL) users is challenging due to communication barriers.
- Existing computer vision and medical imaging methods for dementia assessment have limitations.
Purpose of the Study:
- To develop and evaluate machine learning models for real-time hand movement trajectory tracking in BSL users.
- To improve early identification of dementia and other neurological impairments in the Deaf population.
Main Methods:
- Utilized normal 2D videos to analyze sign language space envelope (trajectories, depth, speed) and facial expressions.
- Implemented two hand movement trajectory tracking models: skin color segmentation and Part Affinity Fields (OpenPose Skeleton Model).
- Focused on accurate segmentation of objects for precise real-time hand trajectory analysis.
Main Results:
- The Part Affinity Fields model demonstrated enhanced accuracy and robustness in tracking hand sign trajectories compared to skin color segmentation.
- Distinct patterns in facial and trajectory motion data were identified.
Conclusions:
- The developed models offer a promising tool for the early screening of dementia in Deaf BSL users.
- The approach can also aid in assessing other neurological impairments like stroke and Parkinson's disease that involve motor changes.
