We present novel approaches involving generative adversarial networks and
diffusion models in order to synthesize high quality, live and spoof
fingerprint images while preserving features such as uniqueness and diversity.
We generate live fingerprints from noise with a variety of methods, and we use
image translation techniques to translate live fingerprint images to spoof. To
generate different types of spoof images based on limited training data we
incorporate style transfer techniques through a cycle autoencoder equipped with
a Wasserstein metric along with Gradient Penalty (CycleWGAN-GP) in order to
avoid mode collapse and instability. We find that when the spoof training data
includes distinct spoof characteristics, it leads to improved live-to-spoof
translation. We assess the diversity and realism of the generated live
fingerprint images mainly through the Fr\'echet Inception Distance (FID) and
the False Acceptance Rate (FAR). Our best diffusion model achieved a FID of
15.78. The comparable WGAN-GP model achieved slightly higher FID while
performing better in the uniqueness assessment due to a slightly lower FAR when
matched against the training data, indicating better creativity. Moreover, we
give example images showing that a DDPM model clearly can generate realistic
fingerprint images.

利用生成对抗网络和扩散模型，我们提出了新颖的方法来合成高质量、真实和仿冒指纹图像，同时保留独特性和多样性特征。通过多种方法从噪声生成真实的指纹图像，并利用图像转换技术将真实的指纹图像转换为仿冒的指纹图像。通过循环自动编码器和梯度惩罚加权里程碑（CycleWGAN-GP）等风格转换技术，结合 Wasserstein 距离指标，我们实现了基于有限训练数据生成不同类型的仿冒图像，以避免模式崩溃和不稳定性。我们发现，当仿冒训练数据包含明显的仿冒特征时，可以改善从真实到仿冒的转换。我们主要通过 Fréchet Inception Distance（FID）和 False Acceptance Rate（FAR）评估生成的真实指纹图像的多样性和逼真性。我们最佳的扩散模型达到了 15.78 的 FID。而相比之下，WGAN-GP 模型在独特性评估方面表现更好，因其在与训练数据匹配时的稍低 FAR，表明更好的创造力。此外，我们给出了示例图像，清楚地显示了 DDPM 模型能够生成逼真的指纹图像。