Archival Faces: Detection of Faces in Digitized Historical Documents

Archival Faces Dataset This is a YOLO-formatted detection dataset for archival documents, specifically designed for facial detection and suitable for evaluation datasets or cross-validation experiments. Dataset Overview The Archival Faces dataset contains historical face images formatted for use with YOLO (You Only Look Once) object detection frameworks. Format All annotations follow the YOLO format: Each image has a corresponding .txt file with the same name Each line in the annotation file represents one face Format: class_id x_center y_center width height right_eye_x right_eye_y right_eye_visibility left_eye_x left_eye_y left_eye_visibility nose_x nose_y nose_visibility right_mouth_corner_x right_mouth_corner_y right_mouth_corner_visibility left_mouth_corner_x left_mouth_corner_y left_mouth_corner_visibility All values are coordinated normalized between 0 and 1, and visibility is always 1 class_id It is always zero since there is only one class (face) Dataset Structure The dataset is organized into 10 splits for cross-validation (k=10, k=2, k=5) and contains the following structure: ArchivalFaces/ ├── fold_0/ │ ├── images/ │ └── labels/ ├── fold_1/ │ ├── images/ │ └── labels/ ... ├── fold_9/ │ ├── images/ │ └── labels/ ... ├── fold_0.yaml ├── fold_1.yaml ... ├── k=2_fold_0.yaml ├── k=2_fold_1.yaml ... ├── k=5_fold_0.yaml ├── k=5_fold_1.yaml ... └── README.md Usage for Ultralytics YOLO model training (v8.3.92, Python 3.10) Extract ArchivalFaces.zip Change directory to ArchivalFaces/ the one that contains the dataset and requirements.txt Create a virtual environment and install all the dependencies. python -m venv .venv source .venv/bin/activate pip install -r requirements.txt Set the Ultralytics dataset to the root directory of this repository. Either change the config via the command line: yolo settings datasets_dir='/path/to/current/directory' Or add from ultralytics import settings; settings.update({"datasets_dir": "/path/to/current/directory"}) to your training script Train your model on k-fold cross-validation python training_example.py Pre-trained models All cross-validation-trained models are added under ArchivalFaces__models.zip archive. The structure of the archive follows the format: ArchivalFaces__models/ ├── {DATASET}[_{PROCESSING_DATE}_k={CROSS_VALIDATION_CONFIGURATION}]/ │ ├── {MODEL}[_fold=[FOLD]].pt/ │ └── ... └── ... DATASET can be either WiderFace or ArchivalFaces. For Archival Faces, there is also PROCESSING_DATE, either 2024-08-07 or 2024-04-04; and CROSS_VALIDATION_CONFIGURATION Which represents the number of cross-validation splits used for a specific experiment, either k=10, k=5, or k=2. Under each experiment directory, a list of pre-trained models is provided. We consistently report the model type, MODEL which can be either YOLOv8 or YOLO11, in variants N, S, M, and L. Models trained on Archival Faces also have the FOLD number that reports the fold used for model evaluation. All models can be used with the Ultralytics framework, and can be loaded with a few lines of code: from ultralytics import YOLO model = YOLO('/path/to/model.pt') Citation If you use this dataset in your research, please cite: @article{DBLP:journals/corr/abs-2504-00558, author = {Marek Vasko and Adam Herout and Michal Hradis}, title = {Archival Faces: Detection of Faces in Digitized Historical Documents}, journal = {CoRR}, volume = {abs/2504.00558}, year = {2025}, url = {https://doi.org/10.48550/arXiv.2504.00558}, doi = {10.48550/ARXIV.2504.00558}, eprinttype = {arXiv}, eprint = {2504.00558}, biburl = {https://dblp.org/rec/journals/corr/abs-2504-00558.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } @dataset{vasko_2025_15077975, author = {Vaško, Marek and Herout, Adam and Hradiš, Michal and Dvořáková, Martina and Petr, Žabička}, title = {Archival Faces: Detection of Faces in Digitized Historical Documents }, month = mar, year = 2025, publisher = {Zenodo}, version = {1.0}, doi = {10.5281/zenodo.15077975}, url = {https://doi.org/10.5281/zenodo.15077975},} License The dataset is made available for non-commercial use (Attribution-NonCommercial 4.0 International). For commercial use, please get in touch with the authors to obtain a commercial license.# 档案人脸数据集（Archival Faces Dataset） 本数据集为适配YOLO（You Only Look Once）格式的目标检测数据集，面向档案类文档，专为面部检测任务打造，可作为评估数据集或用于交叉验证实验。 ## 数据集概览 档案人脸数据集包含适配YOLO（You Only Look Once）目标检测框架的历史人脸图像。 ## 标注格式 所有标注均遵循YOLO格式： 每张图像对应一个同名的`.txt`标注文件，标注文件中的每一行对应一个人脸。标注格式如下： `class_id x_center y_center width height right_eye_x right_eye_y right_eye_visibility left_eye_x left_eye_y left_eye_visibility nose_x nose_y nose_visibility right_mouth_corner_x right_mouth_corner_y right_mouth_corner_visibility left_mouth_corner_x left_mouth_corner_y left_mouth_corner_visibility` 所有坐标值均归一化至0至1区间，可见性字段恒为1。由于仅包含人脸一个类别，故`class_id`恒为0。 ## 数据集结构 本数据集被划分为10个折以支持交叉验证（支持k=10、k=2、k=5三种配置），整体目录结构如下： ArchivalFaces/ ├── fold_0/ │ ├── images/ │ └── labels/ ├── fold_1/ │ ├── images/ │ └── labels/ ... ├── fold_9/ │ ├── images/ │ └── labels/ ... ├── fold_0.yaml ├── fold_1.yaml ... ├── k=2_fold_0.yaml ├── k=2_fold_1.yaml ... ├── k=5_fold_0.yaml ├── k=5_fold_1.yaml ... └── README.md ## 使用方法（适配Ultralytics YOLO模型训练，版本v8.3.92，Python 3.10） 1. 解压`ArchivalFaces.zip` 2. 切换至包含数据集与`requirements.txt`的`ArchivalFaces/`目录 3. 创建虚拟环境并安装所有依赖： bash python -m venv .venv source .venv/bin/activate pip install -r requirements.txt 4. 设置Ultralytics数据集根目录： - 可通过命令行修改配置： bash yolo settings datasets_dir='/path/to/current/directory' - 或在训练脚本中添加如下代码： python from ultralytics import settings settings.update({"datasets_dir": "/path/to/current/directory"}) 5. 执行k折交叉验证训练： bash python training_example.py ## 预训练模型 所有经交叉验证训练得到的模型已打包至`ArchivalFaces__models.zip`存档，存档目录结构如下： ArchivalFaces__models/ ├── {DATASET}[_{PROCESSING_DATE}_k={CROSS_VALIDATION_CONFIGURATION}]/ │ ├── {MODEL}[_fold=[FOLD]].pt/ │ └── ... └── ... 其中，`DATASET`可为`WiderFace`或`ArchivalFaces`。对于档案人脸数据集，`PROCESSING_DATE`可为`2024-08-07`或`2024-04-04`；`CROSS_VALIDATION_CONFIGURATION`代表特定实验所用的交叉验证折数，可为`k=10`、`k=5`或`k=2`。每个实验目录下均提供预训练模型列表，模型类型`MODEL`可为`YOLOv8`或`YOLO11`，包含N、S、M、L四种变体。在档案人脸数据集上训练的模型还会标注训练所用的折数`FOLD`。 所有模型均可通过Ultralytics框架加载使用，仅需数行代码即可完成加载： python from ultralytics import YOLO model = YOLO('/path/to/model.pt') ## 引用方式 若您在研究中使用本数据集，请引用如下文献： bibtex @article{DBLP:journals/corr/abs-2504-00558, author = {Marek Vasko and Adam Herout and Michal Hradis}, title = {Archival Faces: Detection of Faces in Digitized Historical Documents}, journal = {CoRR}, volume = {abs/2504.00558}, year = {2025}, url = {https://doi.org/10.48550/arXiv.2504.00558}, doi = {10.48550/ARXIV.2504.00558}, eprinttype = {arXiv}, eprint = {2504.00558}, biburl = {https://dblp.org/rec/journals/corr/abs-2504.00558.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} } @dataset{vasko_2025_15077975, author = {Vaško, Marek and Herout, Adam and Hradiš, Michal and Dvořáková, Martina and Petr, Žabička}, title = {Archival Faces: Detection of Faces in Digitized Historical Documents}, month = mar, year = 2025, publisher = {Zenodo}, version = {1.0}, doi = {10.5281/zenodo.15077975}, url = {https://doi.org/10.5281/zenodo.15077975}, } ## 许可协议 本数据集仅可用于非商业用途（采用Attribution-NonCommercial 4.0 International许可）。如需商业使用，请联系作者获取商业授权。