I/UCRC Phase II: Center for Identification Technology Research

I/UCRC 第二期：识别技术研究中心

• 批准号: 1650474
• 负责人: Matthew Valenti
• 金额: $ 50万
• 依托单位: West Virginia University Research Corporation
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-03-15 至 2025-02-28
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1650474&HistoricalAwards=false
• 关键词: UCRC; Phase; II; Center; Identification

The Center for Identification Technology Research (CITeR) is an Industry/University Cooperative Research Center (I/UCRC) that is focused on developing and championing technologies and systems for managing the identity of individuals. Having a provable and verifiable identity is necessary for an individual to function in modern society. Working in partnership with government and industry stakeholders, CITeR advances the state of the art in human identification capabilities through coordinated university research related to providing, confirming, and determining identity. Its overall focus is on human analytics, identity science, biometric analysis, and technical implementation of privacy and policy. The WVU site provides innovations related to the increased use of biomolecular analysis (e.g., rapid DNA), cloud computing, mobile devices (e.g., smartphones), and video analytics. These innovations help to protect society and improve the national defense by providing pathways for identifying bad actors, while advancing the science of computing, analytics, and signal processing. CITeR engages graduate students and undergraduates in research, is active in outreach to K-12 students, and actively identifying and addressing the educational needs of next-generation professionals in the identification technology arena. The WVU site brings to the Center its first-ever undergraduate degree specifically focused on biometrics (B.S. in Biometric Systems) and is positioned in proximity to the expanding hub of biometric activity that has arisen in North Central West Virginia.The WVU Site will focus on four technical areas related to CITeR's technical area of Identity: (1) Biomolecular biometrics, (2) Cross-modal and cross-spectral matching, (3) Mobile and cloud biometrics, and (4) Video analytics. Recent advances in rapid DNA will be leveraged to provide tools and techniques to aid investigators, for instance, by providing the capability to extract small amounts of DNA from fingerprints. Cross-modal and cross-spectral matching provide improved ways to recognize subjects in unconstrained environments; for instance, by comparing thermal-to-visible images, thermal surveillance imagery can be compared with visible gallery imagery. Empowered by the cloud, mobile biometrics can improve convenience, but technical solutions must take privacy and security into account. Video analytics can allow subjects to be tracked across multiple camera views and allow their actions to be recognized.

识别技术研究中心（CITeR）是一个工业/大学合作研究中心（I/UCRC），专注于开发和支持用于管理个人身份的技术和系统。 拥有一个可证明和可核实的身份是个人在现代社会中发挥作用的必要条件。 CITeR与政府和行业利益相关者合作，通过与提供，确认和确定身份有关的协调大学研究，推进人类识别能力的最新发展。 其总体重点是人类分析，身份科学，生物识别分析以及隐私和政策的技术实施。 WVU网站提供与生物分子分析的增加使用相关的创新（例如，快速DNA）、云计算、移动的设备（例如，智能手机）和视频分析。 这些创新有助于保护社会，通过提供识别不良行为者的途径来改善国防，同时推进计算，分析和信号处理科学。 CITeR从事研究生和本科生的研究，积极推广到K-12学生，并积极确定和解决下一代专业人员在识别技术竞技场的教育需求。 WVU网站为该中心带来了有史以来第一个专门针对生物识别技术的本科学位（B.S. WVU网站将专注于与CITeR的身份识别技术领域相关的四个技术领域：（1）生物分子生物识别，（2）跨模态和跨光谱匹配，（3）移动的和云生物识别，以及（4）视频分析。 将利用快速DNA方面的最新进展提供工具和技术，以协助调查人员，例如，提供从指纹中提取少量DNA的能力。 交叉模态和交叉光谱匹配提供了在不受约束的环境中识别主体的改进方法;例如，通过比较热图像与可见光图像，可以将热监视图像与可见光画廊图像进行比较。借助云技术，移动的生物识别技术可以提高便利性，但技术解决方案必须考虑隐私和安全性。视频分析可以允许跨多个摄像机视图跟踪主体，并允许识别他们的动作。

项目成果

Contactless Fingerprints: Differential Performance for Fingers of Varying Size and Ridge Density

非接触式指纹：不同尺寸和脊线密度的手指的不同性能

• DOI: 10.1109/biosig58226.2023.10346002
• 发表时间: 2023
• 期刊: 22nd International Conference of the Biometrics Special Interest Group (BIOSIG 2023
• 作者: King, Carson;Garrett, Evan;Berti, Aeddon;Nasrabadi, Nasser;Dawson, Jeremy
• 通讯作者: Dawson, Jeremy

Juvenile Morph Dataset: A Study of Attack Detectability and Recognition Vulnerability

Juvenile Morph 数据集：攻击可检测性和识别漏洞的研究

• DOI: 10.1109/hst56032.2022.10025448
• 发表时间: 2022
• 期刊: uvenile Morph Dataset: A Study of Attack Detectability and Recognition Vulnerability
• 作者: O'Haire, Kelsey;Soleymani, Sobhan;Price, Samuel;Nasrabadi, Nasser M.
• 通讯作者: Nasrabadi, Nasser M.

Improving Face Recognition from Caption Supervision with Multi-Granular Contextual Feature Aggregation

• DOI: 10.1109/ijcb57857.2023.10448749
• 发表时间: 2023-08
• 期刊: 2023 IEEE International Joint Conference on Biometrics (IJCB)
• 作者: M. Hasan;N. Nasrabadi

Synthesis-Guided Feature Learning for Cross-Spectral Periocular Recognition

用于跨光谱眼周识别的综合引导特征学习

• DOI: 10.1109/fg52635.2021.9667086
• 发表时间: 2021
• 期刊: 2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021
• 作者: Poster, Domenick;Nasrabadi, Nasser
• 通讯作者: Nasrabadi, Nasser

Adversarial Machine Learning in Malware Detection: Arms Race between Evasion Attack and Defense

• DOI: 10.1109/eisic.2017.21
• 发表时间: 2017-09
• 期刊: 2017 European Intelligence and Security Informatics Conference (EISIC)
• 作者: Lingwei Chen;Yanfang Ye;T. Bourlai