A FRAMEWORK FOR COVARIATE-SPECIFIC ROC CURVE ESTIMATION, WITH APPLICATION TO BIOMETRIC RECOGNITION

• 成果类型: Article
• 署名作者: Zhu, Xiaochen; Slawski, Martin; Tang, Liansheng
• 署名单位: George Mason University; State University System of Florida; University of Central Florida
• 刊物名称: ANNALS OF APPLIED STATISTICS
• ISSN/ISSBN: 1932-6157
• DOI: 10.1214/23-AOAS1738
• 发表日期: 2023
• 页码: 2821-2842
• 关键词: composite quantile regression; accuracy; selection; MODEL; AREA

摘要

Biometric traits, such as fingerprints, facial images, and teeth impres-sions, are often used in forensic analysis to identify crime suspects. Matching such biometric traits is not perfect, and recent reports have indicated the need for quantifiable measures of error rates for (these) possible matches. Often, comparisons between two sets of a trait are scored with a higher score indi-cating a higher likelihood that the sets are a match. Adjustment of the cutoff for which a match is declared yields a trade-off between false positive and false negative decisions that can be represented by an ROC curve. In this pa-per we study modeling of such ROC curves conditional on covariates, for example, demographic information about source subjects, quality properties of the underlying biometric measurements, or characteristics of forensic ex-aminers; quantifying how error rates vary in dependence of such covariates is often considerably more meaningful in biometrics and forensics than the raw error rates based on the pooled data. We herein develop a framework for estimating covariate-specific ROC curves that integrates robustness, het-eroscedasticity, and stochastic ordering. The latter is of specific relevance in the given application since biometric recognition systems are typically cali-brated to assign higher scores to matching pairs than to nonmatching pairs. The proposed methodology is demonstrated on accuracy of face recognition and fingerprint matching and also has potential in other domains of applica-tion like medical diagnostics.