Internal Structure Attention Network for Fingerprint Presentation Attack Detection From Optical Coherence Tomography

As a non-invasive optical imaging technique, optical coherence tomography (OCT) has proven promising for automatic fingerprint recognition system (AFRS) applications. Diverse approaches have been proposed for OCT-based fingerprint presentation attack detection (PAD). However, considering the complexity and variety of PA samples, it is extremely challenging to increase the generalization ability with the limited PA dataset. To solve the challenge, this paper presents a novel supervised learning-based PAD method, denoted as internal structure attention PAD (ISAPAD). ISAPAD applies prior knowledge to guide network training. Specifically, the proposed dual-branch architecture in ISAPAD can not only learn global features from the OCT images, but also concentrate on the layered structure feature which come from the internal structure attention module (ISAM). The simple yet effective ISAM enables the network to obtain layered segmentation features exclusively belonging to Bonafide from noisy OCT volume data. By incorporating effective training strategies and PAD score generation rules, ISAPAD ensures reliable PAD performance even with limited training data. Extensive experiments and visualization analysis substantiate the effectiveness of the proposed method for OCT PAD.