Recapturing attack of document images is a topic with few research attention. However, such attack can be employed as a simple but effective anti-forensic tool for digital document images. In this work, we present a high quality captured and recaptured image dataset of some representative identity documents to facilitate the study of this important issue. To highlight the risks posed by such attack, we evaluate some popular off-the-shelf machine learning-based approaches with our database under different experimental protocols. Experimental results reveal the risks of existing document recapture detection algorithms under uncontrolled application scenarios.

中文翻译：

---

捕获文件的数字图像取证数据库

重新捕获文档图像的攻击是一个很少有研究关注的话题。但是，这种攻击可以用作数字文档图像的简单但有效的取证工具。在这项工作中，我们提出了一些具有代表性的身份证明文件的高质量捕获和重新捕获的图像数据集，以方便对该重要问题的研究。为了突出这种攻击带来的风险，我们在不同的实验协议下，使用我们的数据库评估了一些流行的基于现成机器学习的方法。实验结果揭示了在不受控制的应用场景下现有文档重新捕获检测算法的风险。