Related Experiment Video
Updated: May 18, 2026
09:30
Tissue Characterization after a New Disaggregation Method for Skin Micro-Grafts Generation
Published on: March 4, 2016
A study of hand back skin texture patterns for personal identification and gender classification
1Biometrics Research Center, Department of Computing, The Hong Kong Polytechnic University, Kowloon, Hong Kong. csjxie@comp.polyu.edu.hk
Sensors (Basel, Switzerland)
|September 27, 2012
Summary
Human hand back skin texture (HBST) patterns are unique for individuals. This study demonstrates HBST
Area of Science:
- Biometrics
- Pattern Recognition
- Computer Vision
Background:
- Human hand back skin texture (HBST) exhibits unique, consistent patterns per individual.
- Existing biometric methods often focus on fingerprints or iris scans.
Purpose of the Study:
- To investigate the potential of HBST patterns for personal identification and gender classification.
- To develop and evaluate an efficient method for HBST pattern recognition.
Main Methods:
- A specialized system was developed to capture HBST images, creating a database of 1,920 images from 80 individuals.
- Textons were learned using sparse representation (SR) with l(1)-minimization on filter bank responses.
- A representation coefficient histogram was constructed from SR, serving as the skin texture feature for classification.
Main Results:
- The proposed texton learning and SR-based method effectively classified HBST patterns.
- Experiments demonstrated the efficacy of HBST features in personal identification.
- The study also showed successful gender classification using HBST patterns.
Conclusions:
- HBST patterns offer a viable biometric trait for human identification.
- HBST analysis can contribute to gender classification systems.
- This research introduces a novel approach to utilizing skin texture for biometric applications.
