用于人脸识别系统中伪装与欺骗检测的联合基于特征的框架
A Combined Feature-Based Framework for Disguise and Spoofing Detection in Face Recognition Systems
浏览论文内容
中文总结 AI 辅助
本文提出并比较五种联合特征提取分类流水线，在单一框架内检测人脸识别系统的伪装与欺骗，HPM性能最一致，LPM欺骗检测准确率最高，揭示经典特征在欺骗敏感性与伪装鲁棒性间的权衡。
中文摘要 AI 辅助
人脸识别系统面临两种不同且通常相互独立的失效模式：欺骗（即冒充者出示授权用户的照片或视频）和伪装（即合法用户因配饰、面部毛发、光照或姿态导致外观与注册模板不同而被拒绝）。本文提出并比较了五个联合特征提取与分类流水线，在单一框架内解决这两个问题：PM（主成分分析与最小欧氏距离MED）、LPM（局部二值模式与主成分分析和MED）、HPM（方向梯度直方图与主成分分析和MED）、SM（加速鲁棒特征与MED）以及HM（哈里斯角点特征与MED）。每个流水线遵循包含预处理、特征提取、特征过滤和分类的通用两阶段流程。这些方法在来自FEI、伪装人脸数据库和NUAA数据库的115个受试者上进行训练，并在六种测试条件下评估，涵盖混合外观、正面人脸、暗光照明、左转和右转姿态以及照片欺骗尝试。基于HOG的流水线（HPM）在所有条件下实现了最一致的性能，混合外观伪装的准确率为94.59%，姿态和光照变体的准确率为81.5%-93.2%，欺骗检测准确率为91.67%；而基于LBP的流水线（LPM）实现了最高的欺骗检测准确率（93.2%），但对姿态变化的鲁棒性较弱。这些结果表明，经典特征表示在欺骗敏感性和伪装鲁棒性之间存在可衡量的权衡，为结论部分讨论的深度学习和跨数据库扩展提供了动机。
英文摘要
Face recognition systems face two distinct, commonly-separated failure modes: spoofing, where an impostor presents a photograph or video of an authorized user, and disguise, where a legitimate user is rejected because their appearance differs from their enrolled template due to accessories, facial hair, illumination, or pose. This paper proposes and compares five combined feature-extraction and classification pipelines that address both problems within a single framework: PM (PCA and Minimum Euclidean Distance, MED), LPM (Local Binary Patterns with PCA and MED), HPM (Histogram of Oriented Gradients with PCA and MED), SM (Speeded-Up Robust Features with MED), and HM (Harris corner features with MED). Each pipeline follows a common two-phase process comprising pre-processing, feature extraction, feature filtering, and classification. The methods were trained on 115 subjects drawn from the FEI, Disguised Faces Database, and NUAA databases and evaluated on six test conditions covering mixed appearances, frontal faces, dark illumination, left- and right-turned poses, and photo-spoofing attempts. The HOG-based pipeline (HPM) achieved the most consistent performance across conditions, with 94.59% accuracy on mixed-appearance disguise, 81.5-93.2% across pose and illumination variants, and 91.67% on spoofing, while the LBP-based pipeline (LPM) achieved the second-highest spoofing-detection accuracy (93.2%), behind PM (96.67%), but weaker robustness to pose change. These results reveal a measurable trade-off between spoof sensitivity and disguise robustness among classical feature representations, motivating the deep-learning and cross-database extensions discussed in the concluding sections.
发表机构
- University of Colombo School of Computing (UCSC), University of Colombo（科伦坡大学计算机科学学院，科伦坡大学）
机构由 AI 辅助整理，请以论文原文为准。
