EAGER: Biometric Authentication using Noncontact Cardiovascular Signals

EAGER：使用非接触式心血管信号进行生物识别认证

• 批准号: 2136915
• 负责人: Amos Abbott
• 金额: $ 18.77万
• 依托单位: Virginia Polytechnic Institute and State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-15 至 2023-04-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2136915&HistoricalAwards=false
• 关键词: EAGER; Biometric; Authentication; using; Noncontact

In our increasingly interconnected society, user authentication - procedures for verifying that individuals are who they claim to be - is important for improving the security of digital systems. Authentication protocols commonly involve combinations of something the user knows (such as a password) or has (such as a card or fob), and biometrics (such as the recognition of a fingerprint). This project develops novel biometric approaches based on the activity of the heart. Because shape and physiology of the cardiovascular system differ from person to person, it is possible to detect significant differences related to blood flow for different individuals. The project introduces methods for detecting information related to the cardiovascular system using a video camera, at the level of detail needed to perform user authentication. The project's broader significance is the potential use of these new techniques, as well as a dataset of measurements collected from several individuals for cybersecurity and health care research and applications.The underlying phenomenon in this project is photoplethysmography, which is the use of illumination-based sensors to record local volumetric changes in peripheral blood circulation. The investigators use video cameras to obtain measurements of cardiovascular activity, with the motivation that noncontact measurements are more convenient and unobtrusive than using devices that touch the skin. An emphasis of the project is the use of machine-learning techniques to analyze signals from videos of the human face, to extract features that can distinguish individuals based solely on cardiovascular activity. The research includes characterization of camera parameters and illumination conditions. The primary goal is to demonstrate that the resulting system can be used for user authentication. Potential contributions of this project include improved security of digital systems, along with better understanding of the cardiovascular system.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

在我们日益相互联系的社会中，用户身份验证——核实个人身份的程序——对提高数字系统的安全性非常重要。身份验证协议通常涉及用户知道的东西（如密码）或拥有的东西（如卡片或钱包）和生物识别技术（如指纹识别）的组合。该项目开发了基于心脏活动的新型生物识别方法。由于心血管系统的形状和生理因人而异，因此可以检测到不同个体之间与血流相关的显著差异。该项目介绍了使用摄像机检测心血管系统相关信息的方法，在执行用户身份验证所需的详细级别上。该项目的更广泛意义在于这些新技术的潜在用途，以及从几个人那里收集的用于网络安全和医疗保健研究和应用的测量数据集。这个项目的潜在现象是光体积脉搏图，它是使用基于照明的传感器来记录周围血液循环的局部体积变化。研究人员使用摄像机来测量心血管活动，其动机是非接触式测量比使用接触皮肤的设备更方便、更不显眼。该项目的一个重点是使用机器学习技术来分析人脸视频中的信号，以提取仅基于心血管活动就能区分个体的特征。研究包括相机参数的表征和照明条件。主要目标是演示生成的系统可用于用户身份验证。这个项目的潜在贡献包括提高数字系统的安全性，以及更好地了解心血管系统。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。