arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1401.4489cs.CVcs.LGstat.ML
收藏

可撤销生物特征识别中的随机投影分析

An Analysis of Random Projections in Cancelable Biometrics

SUNY Buffalo(纽约州立大学布法罗分校);Samsung(三星)

Devansh Arpit, Ifeoma Nwogu, Gaurav Srivastava, Venu Govindaraju

摘要:

随着对安全性的日益关注,对利用\emph{cancelable biometric}技术的高度安全的基于物理生物特征的认证系统的需求正在增加。由于可取消模板生成的问题涉及模板安全性和匹配性能之间的权衡,因此许多成功生成高质量可取消生物特征的最新算法都将随机投影作为其早期处理步骤之一。因此,本文提出了一个正式的分析,为什么随机预测是一个必不可少的步骤,在可取消的生物识别。通过正式定义数据集的\textit{Independent Subspace Structure}的概念,可以证明随机投影保留了从独立线性子空间的并集生成的数据向量的子空间结构。上的最小数量的随机向量所需的约束,这也是派生和所示的依赖于数据样本的数量,不仅在独立的子空间,但在不相交的子空间设置以及。在真实世界的人脸识别数据集的实证结果详细支持的理论分析。

英文摘要:

With increasing concerns about security, the need for highly secure physical biometrics-based authentication systems utilizing \emph{cancelable biometric} technologies is on the rise. Because the problem of cancelable template generation deals with the trade-off between template security and matching performance, many state-of-the-art algorithms successful in generating high quality cancelable biometrics all have random projection as one of their early processing steps. This paper therefore presents a formal analysis of why random projections is an essential step in cancelable biometrics. By formally defining the notion of an \textit{Independent Subspace Structure} for datasets, it can be shown that random projection preserves the subspace structure of data vectors generated from a union of independent linear subspaces. The bound on the minimum number of random vectors required for this to hold is also derived and is shown to depend logarithmically on the number of data samples, not only in independent subspaces but in disjoint subspace settings as well. The theoretical analysis presented is supported in detail with empirical results on real-world face recognition datasets.

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。

↑