Related Experiment Video
Updated: Jul 8, 2025
06:08
Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
Published on: May 5, 2011
16.8K
Living-skin Detection using Multi-layer Skin Property Perceived by the Structured Light.
Summary
This study introduces a novel living-skin detection method for face recognition systems. By analyzing laser spot blur on skin, it effectively combats face fraud with high accuracy.
Area of Science:
- Biometrics
- Computer Vision
- Optical Sensing
Background:
- Face recognition systems are vulnerable to spoofing attacks using fake faces.
- Existing living-skin detection methods require improvement in accuracy and robustness.
Purpose of the Study:
- To propose a new living-skin detection technique leveraging the multi-layer skin structure.
- To develop an algorithm differentiating skin from non-skin based on laser spot blur analysis.
Main Methods:
- Utilizing structured light to project laser spots onto surfaces.
- Analyzing the blurriness of laser spots caused by skin's unique photon penetration and reflection properties.
- Developing a blur detection algorithm for distinguishing real skin from artificial materials.
Main Results:
- Achieved an average precision of 96.7% for living-skin detection.
- Obtained an average recall of 82.2% and an F1-score of 88.6% on a dataset of 20 adult subjects.
- Demonstrated the effectiveness of the multi-layer skin property approach.
Conclusions:
- The proposed laser spot blur analysis offers a promising new method for living-skin detection.
- This technique effectively enhances anti-spoofing capabilities in face recognition systems.
- Exploiting multi-layer skin properties provides a robust solution for biometric security.
