EXPRESSNET：用于指纹呈现攻击检测的可解释残差 Slim 网络
EXPRESSNET: An Explainable Residual Slim Network for Fingerprint Presentation Attack Detection
AI总结：
本文提出 EXPRESSNET，通过编码器-解码器热图生成、通道注意力与改进 ResNet 端到端区分真假指纹，并在 Livdet 2011–2019 上取得优于现有方法的准确率。
摘要：
呈现攻击是自动指纹识别系统安全中持续存在的一个具有挑战性的问题。本文提出了一种新颖的可解释残差 slim 网络，通过表征输入指纹样本中的视觉特征来检测呈现攻击。该网络的编码器-解码器与通道注意力模块共同将输入样本转换为其热图表征，而改进的残差卷积神经网络分类器则区分真实指纹与伪造指纹。热图生成器模块和改进的 ResNet 分类器的整个架构以端到端方式协同工作。所提模型的性能在基准活体检测竞赛数据库（即 Livdet 2011、2013、2015、2017 和 2019）上得到验证，并在这些数据库上分别取得 96.86%、99.84%、96.45%、96.07%、96.27% 的分类准确率。所提模型的性能与现有最先进技术进行了比较，结果表明，在呈现攻击检测的基准协议中，所提方法在分类准确率方面优于最先进方法。
英文摘要：
Presentation attack is a challenging issue that persists in the security of automatic fingerprint recognition systems. This paper proposes a novel explainable residual slim network that detects the presentation attack by representing the visual features in the input fingerprint sample. The encoder-decoder of this network along with the channel attention block converts the input sample into its heatmap representation while the modified residual convolutional neural network classifier discriminates between live and spoof fingerprints. The entire architecture of the heatmap generator block and modified ResNet classifier works together in an end-to-end manner. The performance of the proposed model is validated on benchmark liveness detection competition databases i.e. Livdet 2011, 2013, 2015, 2017, and 2019 and the classification accuracy of 96.86\%, 99.84\%, 96.45\%, 96.07\%, 96.27\% are achieved on them, respectively. The performance of the proposed model is compared with the state-of-the-art techniques, and the proposed method outperforms state-of-the-art methods in benchmark protocols of presentation attack detection in terms of classification accuracy.
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。
