Face liveness detection is essential for securing biometric authentication systems against spoofing attacks,including printed photos,replay videos,and 3D masks.This study systematically evaluates pre-trained CNN model...Face liveness detection is essential for securing biometric authentication systems against spoofing attacks,including printed photos,replay videos,and 3D masks.This study systematically evaluates pre-trained CNN models—DenseNet201,VGG16,InceptionV3,ResNet50,VGG19,MobileNetV2,Xception,and InceptionResNetV2—leveraging transfer learning and fine-tuning to enhance liveness detection performance.The models were trained and tested on NUAA and Replay-Attack datasets,with cross-dataset generalization validated on SiW-MV2 to assess real-world adaptability.Performance was evaluated using accuracy,precision,recall,FAR,FRR,HTER,and specialized spoof detection metrics(APCER,NPCER,ACER).Fine-tuning significantly improved detection accuracy,with DenseNet201 achieving the highest performance(98.5%on NUAA,97.71%on Replay-Attack),while MobileNetV2 proved the most efficient model for real-time applications(latency:15 ms,memory usage:45 MB,energy consumption:30 mJ).A statistical significance analysis(paired t-tests,confidence intervals)validated these improvements.Cross-dataset experiments identified DenseNet201 and MobileNetV2 as the most generalizable architectures,with DenseNet201 achieving 86.4%accuracy on Replay-Attack when trained on NUAA,demonstrating robust feature extraction and adaptability.In contrast,ResNet50 showed lower generalization capabilities,struggling with dataset variability and complex spoofing attacks.These findings suggest that MobileNetV2 is well-suited for low-power applications,while DenseNet201 is ideal for high-security environments requiring superior accuracy.This research provides a framework for improving real-time face liveness detection,enhancing biometric security,and guiding future advancements in AI-driven anti-spoofing techniques.展开更多
In recent years, face recognition has often been proposed for personal identification. However, there are many difficulties with face recognition systems. For example, an imposter could Iogin the face recognition syst...In recent years, face recognition has often been proposed for personal identification. However, there are many difficulties with face recognition systems. For example, an imposter could Iogin the face recognition system by stealing the facial photograph of a person registered on the facial recognition system. The secudty of the face recognition system requires a live detection system to prevent system Iogin using photographs of a human face. This paper describes an effective, efficient face live detection method which uses physiological motion detected by estimating the eye blinks from a captured video sequence and an eye contour extraction algorithm. This technique uses the conventional active shape model with a random forest classifier trained to recognize the local appearance around each landmark. This local match provides more robustness for optimizing the fitting procedure. Tests show that this face live detection approach successfully discriminates a live human face from a photograph of the registered person＇s face to increase the face recognition system reliability.展开更多
基金funded by Centre for Advanced Modelling and Geospatial Information Systems(CAMGIS),Faculty of Engineering and IT,University of Technology Sydney.Moreover,Ongoing Research Funding Program(ORF-2025-14)King Saud University,Riyadh,Saudi Arabia,under Project ORF-2025-。
文摘Face liveness detection is essential for securing biometric authentication systems against spoofing attacks,including printed photos,replay videos,and 3D masks.This study systematically evaluates pre-trained CNN models—DenseNet201,VGG16,InceptionV3,ResNet50,VGG19,MobileNetV2,Xception,and InceptionResNetV2—leveraging transfer learning and fine-tuning to enhance liveness detection performance.The models were trained and tested on NUAA and Replay-Attack datasets,with cross-dataset generalization validated on SiW-MV2 to assess real-world adaptability.Performance was evaluated using accuracy,precision,recall,FAR,FRR,HTER,and specialized spoof detection metrics(APCER,NPCER,ACER).Fine-tuning significantly improved detection accuracy,with DenseNet201 achieving the highest performance(98.5%on NUAA,97.71%on Replay-Attack),while MobileNetV2 proved the most efficient model for real-time applications(latency:15 ms,memory usage:45 MB,energy consumption:30 mJ).A statistical significance analysis(paired t-tests,confidence intervals)validated these improvements.Cross-dataset experiments identified DenseNet201 and MobileNetV2 as the most generalizable architectures,with DenseNet201 achieving 86.4%accuracy on Replay-Attack when trained on NUAA,demonstrating robust feature extraction and adaptability.In contrast,ResNet50 showed lower generalization capabilities,struggling with dataset variability and complex spoofing attacks.These findings suggest that MobileNetV2 is well-suited for low-power applications,while DenseNet201 is ideal for high-security environments requiring superior accuracy.This research provides a framework for improving real-time face liveness detection,enhancing biometric security,and guiding future advancements in AI-driven anti-spoofing techniques.
基金Supported by the National Key Basic Research and Development (973) Program of China (No.2007CB311004)
文摘In recent years, face recognition has often been proposed for personal identification. However, there are many difficulties with face recognition systems. For example, an imposter could Iogin the face recognition system by stealing the facial photograph of a person registered on the facial recognition system. The secudty of the face recognition system requires a live detection system to prevent system Iogin using photographs of a human face. This paper describes an effective, efficient face live detection method which uses physiological motion detected by estimating the eye blinks from a captured video sequence and an eye contour extraction algorithm. This technique uses the conventional active shape model with a random forest classifier trained to recognize the local appearance around each landmark. This local match provides more robustness for optimizing the fitting procedure. Tests show that this face live detection approach successfully discriminates a live human face from a photograph of the registered person＇s face to increase the face recognition system reliability.
