LDRNet：实现移动设备上的实时文档定位
LDRNet: Enabling Real-time Document Localization on Mobile Devices
AI总结：
本文提出LDRNet，一种用于移动设备实时身份文档验证的轻量级文档定位模型，通过三个预测分支、等分点补充目标和Line Loss损失函数，在通用文档数据集上实现790 FPS的速度（快47倍）且保持相当的Jaccard指数。
摘要：
随着移动设备上的身份文档验证（IDV）技术在现代商业运营中变得无处不在，身份盗窃和欺诈的风险也在增加。身份文档持有者通常需要参加在线视频面试以防范冒名顶替者。然而，当前的IDV流程依赖于额外的人力来支持在线逐步指导，这既低效又昂贵。现有基于AI的方法的性能无法满足移动设备的实时和轻量级需求。在本文中，我们通过设计一种边缘智能辅助方法来解决这些挑战，以实现实时IDV。为了提高IDV流程的响应速度，我们提出了一种新的移动设备文档定位模型LDRNet，用于实时定位身份文档。在轻量级骨干网络的基础上，我们为LDRNet构建了三个预测分支：角点预测、线边界预测和文档分类。我们设计了新颖的补充目标——等分点，并使用一种名为Line Loss的新损失函数，以提高我们方法的速度和准确性。除了IDV流程外，LDRNet还是各种移动应用中高效可靠的文档定位替代方案。作为证明，我们将LDRNet与在通用文档数据集上定位的其他流行方法的性能进行了比较。实验结果表明，LDRNet的运行速度高达790 FPS，快47倍，同时在单模型和单尺度测试中仍能达到相当的Jaccard指数（JI）。
英文摘要：
While Identity Document Verification (IDV) technology on mobile devices becomes ubiquitous in modern business operations, the risk of identity theft and fraud is increasing. The identity document holder is normally required to participate in an online video interview to circumvent impostors. However, the current IDV process depends on an additional human workforce to support online step-by-step guidance which is inefficient and expensive. The performance of existing AI-based approaches cannot meet the real-time and lightweight demands of mobile devices. In this paper, we address those challenges by designing an edge intelligence-assisted approach for real-time IDV. Aiming at improving the responsiveness of the IDV process, we propose a new document localization model for mobile devices, LDRNet, to Localize the identity Document in Real-time. On the basis of a lightweight backbone network, we build three prediction branches for LDRNet, the corner points prediction, the line borders prediction and the document classification. We design novel supplementary targets, the equal-division points, and use a new loss function named Line Loss, to improve the speed and accuracy of our approach. In addition to the IDV process, LDRNet is an efficient and reliable document localization alternative for all kinds of mobile applications. As a matter of proof, we compare the performance of LDRNet with other popular approaches on localizing general document datasets. The experimental results show that LDRNet runs at a speed up to 790 FPS which is 47x faster, while still achieving comparable Jaccard Index(JI) in single-model and single-scale tests.
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。
