构建评估滤镜对人脸识别影响的框架，发现中美滤镜差异并可恢复识别性能
A Comprehensive Evaluation Framework for the Study of the Effects of Facial Filters on Face Recognition Accuracy
- 设计可控数据集与筛选流程，系统化评估多平台滤镜影响
- 跨文化对比显示中美社交应用滤镜对识别率影响存在显著差异
- 在嵌入空间中可检测并修复滤镜带来的识别偏差，提升准确率
面部滤镜在全球社交媒体用户中已十分普遍。以往研究仅关注特定风格的少量手选滤镜，未能覆盖主流社交平台的广泛滤镜类型。为此，本文提出一个综合性评估框架，包含受控的人脸图像数据集、有原则的滤镜选择机制，以及用于评估滤镜影响的实验方案。通过该框架，以美国的Instagram和Snapchat，以及中国的Meitu和Pitu为例进行案例研究，揭示了跨文化滤镜使用对人脸识别性能的影响差异。此外，研究发现滤镜在人脸嵌入空间中的影响可被有效检测，并可通过恢复手段显著提升识别准确率。
原文摘要 · Abstract (English)
Facial filters are now commonplace for social media users around the world. Previous work has demonstrated that facial filters can negatively impact automated face recognition performance. However, these studies focus on small numbers of hand-picked filters in particular styles. In order to more effectively incorporate the wide ranges of filters present on various social media applications, we introduce a framework that allows for larger-scale study of the impact of facial filters on automated recognition. This framework includes a controlled dataset of face images, a principled filter selection process that selects a representative range of filters for experimentation, and a set of experiments to evaluate the filters' impact on recognition. We demonstrate our framework with a case study of filters from the American applications Instagram and Snapchat and the Chinese applications Meitu and Pitu to uncover cross-cultural differences. Finally, we show how the filtering effect in a face embedding space can easily be detected and restored to improve face recognition performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。