发表机构
Federal University of Paraná; Federal Institute of Mato Grosso（巴拉那联邦大学; 马托格罗索联邦学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出UFPR-PEs这一带有巴西自报种族/肤色标签的人脸识别基准，用于评估人脸识别偏差，结合图像质量分析识别性能的子组差异，为相关研究提供可复现的人口统计学环境。
AI 中文摘要
尽管人脸识别系统已被广泛部署，但在非受控视觉条件下确保其人口统计学可靠性和鲁棒性仍是一项关键挑战。为弥合这一差距，我们提出了UFPR-PEs，这是一个用于人脸识别偏差评估的基准，采用带有官方自报种族/肤色类别的巴西当选政治家公开视频构建。该数据集采用巴西人口普查分类法，包含在以往基准常用的以美国或欧洲为中心的分类体系中无直接对应项的parda类别。我们的基准由压缩后的公开视频构建，并保留了困难样本，以便在现实条件下分析性能。我们描述了构建流程，报告了数据集统计数据，并在验证以及闭集和开集识别场景下评估了人脸识别性能，包括按种族/肤色和困难程度进行的子组分析。结果表明，识别性能随图像质量大幅变化，且子组差异必须结合视觉困难程度共同解释，而非孤立解读。总体而言，UFPR-PEs为在具有挑战性的公开视频条件下研究人脸识别偏差提供了可复现且基于人口统计学的环境。
英文摘要
While face recognition systems are widely deployed, ensuring their demographic reliability and robustness under uncontrolled visual conditions remains a critical challenge. To bridge this gap, we present UFPR-PEs, a benchmark for face recognition bias evaluation using public videos of elected Brazilian politicians annotated with official self-declared race/color categories. The dataset adopts the Brazilian census taxonomy, including the parda category, which has no direct equivalent in the U.S.- or Europe-centric schemas commonly used in prior benchmarks. Our benchmark is built from compressed public video and preserves difficult samples so that performance can be analyzed under realistic conditions. We describe the construction pipeline, report dataset statistics, and evaluate face recognition performance across verification and (closed- and open-set) identification settings, including subgroup analysis by race/color and difficulty level. The results show that recognition performance varies substantially with image quality, and that subgroup gaps must be interpreted jointly with visual difficulty rather than in isolation. Overall, UFPR-PEs provides a reproducible and demographically grounded setting for studying face recognition bias under challenging public video conditions.
CommentsAccepted for presentation at the 2026 Conference on Graphics, Patterns and Images (SIBGRAPI)
