Improving Face Anti-Spoofing for Light Makeup
Author Information
Author(s): Lai Zhimao, Guo Yang, Hu Yongjian, Su Wenkang, Feng Renhai
Primary Institution: China People’s Police University
Hypothesis
How does light makeup affect the performance of face anti-spoofing algorithms?
Conclusion
The proposed face anti-spoofing algorithm shows improved detection capabilities for faces with light makeup compared to existing methods.
Supporting Evidence
- The study created a new database specifically for light makeup faces.
- Most existing face anti-spoofing algorithms performed worse on light makeup faces.
- The proposed algorithm includes innovative components to enhance detection performance.
Takeaway
This study created a special database of faces with light makeup to help computers recognize faces better, even when people wear light makeup.
Methodology
The study developed a face anti-spoofing database for light makeup and evaluated existing algorithms using this database.
Potential Biases
Potential biases in makeup assessment due to subjective evaluations.
Limitations
The study primarily focuses on light makeup and does not address heavy makeup or other accessories.
Participant Demographics
The database includes 50 subjects with varying degrees of makeup.
Statistical Information
P-Value
p<0.05
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website