Cascade Forgery Mining Network for Fingerprint Presentation Attack Detection
2026-07-27 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors study how different parts of a fingerprint image can be harder or easier to analyze for fake signs, which they call Artifact Extraction Difficulty (AED). They use a method to measure AED in different regions of a fingerprint and design a special neural network called CFM-Net that adapts its depth to better detect fake evidence in these regions. They also add a training step, OGAT, to remove personal identity clues while keeping fake detection features intact. Their tests show this approach works better than existing methods, especially on fingerprints with high AED.
Fingerprint presentation attack detectionArtifact extraction difficultyGabor featuresFeature extractionCascade Forgery Mining NetworkAdversarial trainingLivDet datasetsFingerprint spoofingOrientation guidance
Authors
Hongyan Fei, Chuanwei Huang, Zheng Wang, Pengcheng Luo, Jingwei Li, Jufu Feng
Abstract
Fingerprint Presentation Attack Detection (PAD) is a critical component of fingerprint identification systems, serving as a protective measure against unauthorized access. In this paper, we observe that different regions of a fingerprint image can exhibit varying Artifact Extraction Difficulty (AED), with high-AED regions requiring more sophisticated extraction mechanisms to capture more subtle discriminative evidence. To address this issue, we propose to quantify AED using local Gabor feature certainty and partition fingerprint images into multiple regions based on their respective AED values. We then propose an AED guided Cascade Forgery Mining Network (CFM-Net) that employs an adaptive-depth feature extraction architecture to detect more precise and comprehensive artifact evidence across regions with heterogeneous AED values. Furthermore, we introduce an Orientation Guided Adversarial Training (OGAT) module to filter out identity information from PAD features while preserving the integrity of original artifact evidence. Experimental evaluations on LivDet datasets demonstrate the superior performance of our approach compared to state-of-the-art methods and achieve significant improvement in the classification ability of high AED fingerprints.