Fingerprint presentation attack detection (FPAD) is essential in fingerprint identification systems. Noncontact methods such as fingerprint biometrics are becoming popular because they are not affected by skin conditions and there are no hygiene issues. However, most of the existing noncontact FPAD methods are supervised methods with poor generalizability and poor performance during events such as unseen presentation attacks (PAs). Moreover, easily overlooked frequency domain information contributes to the fingerprint antispoofing task. Therefore, we propose a wavelet-based memory-augmented autoencoder that fully utilizes the frequency domain information. Specifically, the model first decomposes the input image into high- and low-frequency information and extracts features separately. Subsequently, we propose a frequency complementary connection (FCC) module to realize the fusion and complementation of frequency domain information at the feature level. Moreover, a memory distance expansion loss is proposed to keep the memory module diverse. Experiments are conducted to verify the effectiveness of the method. The code of our model is available on https://github.com/SuperIOyht/WaveMemAE .

中文翻译：

---

用于非接触式指纹呈现攻击检测的基于小波的记忆自动编码器


指纹呈现攻击检测（FPAD）在指纹识别系统中至关重要。指纹生物识别等非接触式方法越来越流行，因为它们不受皮肤状况的影响，也不存在卫生问题。然而，大多数现有的非接触式 FPAD 方法都是有监督的方法，在诸如看不见的呈现攻击（PA）等事件中泛化性较差且性能较差。此外，容易被忽视的频域信息有助于指纹反欺骗任务。因此，我们提出了一种基于小波的记忆增强自动编码器，充分利用频域信息。具体来说，该模型首先将输入图像分解为高频和低频信息，并分别提取特征。随后，我们提出了频率互补连接（FCC）模块来实现特征级别频域信息的融合和互补。此外，提出了存储距离扩展损耗以保持存储模块的多样性。并通过实验验证了该方法的有效性。我们模型的代码可以在 https://github.com/SuperIOyht/WaveMemAE 上找到。