Related Experiment Video
Updated: May 1, 2026
08:27
Three-Dimensional Finger Motion Tracking during Needling: A Solution for the Kinematic Analysis of Acupuncture Manipulation
Published on: October 28, 2021
2.7K
Smart touchless palm sensing via palm adjustment and dynamic registration
Dandan Fan1, Xu Liang2, Chunsheng Zhang1
1School of Data Science, The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), Shenzhen, China.
Nature Communications
|March 26, 2025
Summary
This study introduces a new system for touchless palm recognition that overcomes challenges from varying distances and positions. The enhanced method improves accuracy and adaptability in biometric systems.
Area of Science:
- Biometrics and Human-Computer Interaction
- Computer Vision and Image Processing
Background:
- Touchless palm recognition offers benefits like hygiene and privacy.
- Performance degrades due to variations in palm positioning and capture distance.
Purpose of the Study:
- To develop a robust sensing system for touchless palm recognition.
- To address performance degradation caused by distance and positioning variations.
Main Methods:
- Investigated distance variations to set optimal registration parameters.
- Proposed an edge-aware, rotation-invariant region of interest alignment method.
- Integrated alignment into a video-sequence-based palm registration framework.
Main Results:
- The proposed method significantly enhances touchless palm recognition performance.
- Improved system adaptability to varying capture conditions.
- Demonstrated effectiveness across diverse datasets.
Conclusions:
- The developed system effectively handles variations in palm positioning and distance.
- The edge-aware alignment method ensures robust spatial alignment.
- This approach advances the reliability of touchless biometric systems.
