使用卷积神经网络和局部二值模式进行呈现攻击检测
Presentation Attack Detection using Convolutional Neural Networks and Local Binary Patterns
AI总结：
本文比较了 Inception-v3、改进的浅层 Spoofnet CNN 和局部二值模式三种方法在人脸与虹膜呈现攻击检测上的表现，并在 ATVS-FIr 和 CASIA 数据集上验证了各自的有效性。
摘要：
近年来，使用生物特征对用户进行身份认证并控制对安全区域的访问已变得极为普遍，生物特征访问控制系统被政府和私营企业广泛采用。然而，如果在部署时未考虑生物特征呈现攻击（也称为欺骗攻击）的可能性，这些系统可能会带来安全风险。呈现攻击是一种严重威胁，因为实施这类攻击不需要大量时间、费用或技能，同时对当前使用的许多生物特征系统仍然有效。本研究比较了三种不同的基于软件的方法，用于图像中的人脸和虹膜呈现攻击检测。第一种方法使用 Inception-v3，这是由 Google 为 ImageNet 挑战赛制作的预训练深度卷积神经网络（CNN），并针对本问题进行了重新训练。第二种方法使用基于修改后的 Spoofnet 架构的浅层 CNN，并进行常规训练。第三种是基于纹理的方法，使用局部二值模式（LBP）。所使用的数据集包括 ATVS-FIr 数据集，其中包含真实和伪造的虹膜图像，以及 CASIA Face Anti-Spoofing Dataset，其中包含真实图像以及扭曲照片、裁剪照片和视频重放呈现攻击。我们还提出了第三组结果，基于 CASIA 图像的裁剪版本。
英文摘要：
The use of biometrics to authenticate users and control access to secure areas has become extremely popular in recent years, and biometric access control systems are frequently used by both governments and private corporations. However, these systems may represent risks to security when deployed without considering the possibility of biometric presentation attacks (also known as spoofing). Presentation attacks are a serious threat because they do not require significant time, expense, or skill to carry out while remaining effective against many biometric systems in use today. This research compares three different software-based methods for facial and iris presentation attack detection in images. The first method uses Inception-v3, a pre-trained deep Convolutional Neural Network (CNN) made by Google for the ImageNet challenge, which is retrained for this problem. The second uses a shallow CNN based on a modified Spoofnet architecture, which is trained normally. The third is a texture-based method using Local Binary Patterns (LBP). The datasets used are the ATVS-FIr dataset, which contains real and fake iris images, and the CASIA Face Anti-Spoofing Dataset, which contains real images as well as warped photos, cut photos, and video replay presentation attacks. We also present a third set of results, based on cropped versions of the CASIA images.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
