Abstract
When digitizing historical archives, it is necessary to search for the faces of celebrities and ordinary people, especially in newspapers, link them to the surrounding text, and make them searchable. Existing face detectors on datasets of scanned historical documents fail remarkably -- current detection tools only achieve around $24\%$ mAP at $50:90\%$ IoU. This work compensates for this failure by introducing a new manually annotated domain-specific dataset in the style of the popular Wider Face dataset, containing 2.2k new images from digitized historical newspapers from the $19^{th}$ to $20^{th}$ century, with 11k new bounding-box annotations and associated facial landmarks. This dataset allows existing detectors to be retrained to bring their results closer to the standard in the field of face detection in the wild. We report several experimental results comparing different families of fine-tuned detectors against publicly available pre-trained face detectors and ablation studies of multiple detector sizes with comprehensive detection and landmark prediction performance results.
Abstract (translated)
在数字化历史档案的过程中，需要识别名人和普通人的面部，并将其与周围的文本关联起来，使其可搜索。然而，在扫描的历史文档数据集上，现有的面部检测器表现不佳——目前的检测工具仅能达到约24% mAP（平均精度）和50:90% IoU（交并比）。为弥补这一不足，本工作引入了一个新的手动标注的专业领域数据集，该数据集模仿了流行的Wider Face数据集风格，包含来自19至20世纪数字化历史报纸的2.2k新图像以及与之相关的11k新边界框注释和面部特征点。 此数据集使得现有检测器能够重新训练以使其结果更接近于现实世界中人脸检测的标准。我们报告了多项实验结果，比较了不同类型的微调后的检测器与公开可用的预训练的人脸检测器，并进行了多种大小检测器的消融研究，提供全面的检测和特征点预测性能数据。
URL
https://arxiv.org/abs/2504.00558
