An Efficient OCT Fingerprint Antispoofing Method Based on ResMamba

Optical coherence tomography (OCT), known for its noncontact and 3D imaging capabilities, has found widespread application in fingerprint antispoofing detection. However, the existing methods rely heavily on single-frame B-scan images, underutilizing the 3D spatial information inherent in OCT volume data. High computational costs further limit its practical applications. Thus, this study proposes an efficient fingerprint antispoofing method which leverages the spatial continuity of OCT volume data to enhance both the accuracy and computational efficiency. Using an OCT system, we collected 320 real fingerprints and 320 spoofed fingerprints. Then, to distinguish between genuine and spoofed fingerprints, we developed the proposed ResMamba model, which is based on an enhanced 3D convolutional network integrated with a state space model (SSM). We extracted regions of interest (ROIs) from B-scan images and segmented them into volume slices for training and classification. The experimental results demonstrate that ResMamba achieved a 0.56% error rate (ERR) and 99.22% area under the curve (AUC), with an inference time of just 11 ms. Furthermore, compared to the existing models, ResMamba effectively balances its accuracy, inference speed, and model size. Ablation studies confirm that integrating the SIC module enhances the model’s robustness. Overall, ResMamba offers an efficient and reliable fingerprint antispoofing solution, outperforming the traditional methods in terms of its accuracy and performance.