OCT Fingerprint Presentation Attack Detection Based on Dual-Branch Reconstruction Differences

作者：Haixia Wang, Kun Xiao, Chengfang Zhu, Ronghua Liang, Yilong Zhang, Peng Chen, Yipeng Liu, Rui Yan · 发表于：IEEE Transactions on Instrumentation and Measurement · 年份：2025 · DOI：10.1109/tim.2025.3565107 · 被引用次数：3 · 研究领域：Biometric Identification and Security

The emergence of Optical Coherence Tomography (OCT) as a non-invasive imaging technique has advanced research in automated fingerprint recognition systems (AFRS). Several methods leveraging OCT for fingerprint presentation attack detection (PAD) have been proposed, offering promising solutions to enhance the security and reliability of biometric authentication systems. However, effectively detecting unknown presentation attacks (PAs) remains a challenging issue. Reconstruction-based strategy that requires only bonafide data for training could be a solution to address the issue of the data dependency. It detects unknown PAs by computing differences between the input image and the reconstructed image. Nevertheless, two key challenges presented in reconstruction-based PAD: style differences introduced during reconstruction and inadequate reconstruction performance when dealing with PA samples, which affect detection performance. To tackle these issues, this study proposed a novel dual-branch reconstruction differences-based presentation attack detection (RePAD) method for fingerprints captured by OCT. The method consists of two distinct branches: the Recovery branch and the Equality branch. The Recovery branch is specifically designed to enhance the network’s ability to reconstruct any inputs into bonafide-like images. A simulated anomaly module is further introduced to generate abnormal images for participation in network training without any pre-knowledge of PAs. Meanwhile, th...