Modelpublic

mdefrance/yolos-base-signature-detection

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

1likes2.3kdownloads

Model Card

YOLOS (base-sized) Model For Handwritten Signature Detection

YOLOS model finetuned to detect handwritten signatures in document images using [tech4humans/signature-detection](https://huggingface.co/datasets/tech4humans/signature-detection) dataset.

Original YOLOS was introduced in the paper You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection by Fang et al. and first released in this repository.

Model description

YOLOS is a Vision Transformer (ViT) trained using the DETR loss. Despite its simplicity, a base-sized YOLOS model is able to achieve 42 AP on COCO validation 2017 (similar to DETR and more complex frameworks such as Faster R-CNN).

—Finetuned by: Mario DEFRANCE
—Repository: mdefrance/signature-detection
—Model type: YOLOS
—License: Apache 2.0 license
—Finetuned from model hustvl/yolos-base

Uses

This model is designed for detecting handwritten signatures in scanned documents, contracts, or forms.

You can try it instantly in your browser here: ![HF Space](https://huggingface.co/spaces/mdefrance/signature-detection-demo)

Direct Use

Here is how to use this model:

python

from datasets import load_dataset
from transformers import pipeline

# Load the tech4humans signature dataset
dataset = load_dataset("samuellimabraz/signature-detection")

# Load the finetuned model
yolos = pipeline(
    task="object-detection",
    model="mdefrance/yolos-base-signature-detection",
    device_map="auto",
)

# Inference on test sample
prediction = yolos(dataset["test"][0].get("image"))

Currently, both the image processor and model support PyTorch.

Out-of-Scope Use

—Fraudulent Use: This model must not be used for forging signatures or any illegal activity. It’s meant for legitimate signature detection in documents.
—Other Objects: Not suitable for detecting non-signature elements in documents.
—Critical Decisions: Should not be solely relied on for high-stakes decisions (e.g., legal or financial) without human validation.

Bias, Risks, and Limitations

—Bias: May not generalize well if training data lacks diversity in signature styles or cultural context.
—Risks: False positives/negatives can occur, impacting document validation.
—Limitations: Performance may degrade on poor-quality images or in challenging visual conditions (e.g., noise, lighting).

Recommendations

—Improve Training Data: Fine-tune with diverse and representative samples to reduce bias.
—Human Oversight: Always include a human review step for critical use cases.
—Image Quality: Use clean, high-resolution images; apply preprocessing if needed.
—Ethical Use: Follow legal and ethical standards, ensuring privacy and responsible deployment.

Training Details

Training Data

The training utilized a dataset built from two public datasets: Tobacco800 and signatures-xc8up, unified and processed in Roboflow. The processed dataset was created by Samuel Lima Braz, and all credit for the dataset preparation goes to him.

Dataset Summary:

—Training: 1,980 images (70%)
—Validation: 420 images (15%)
—Testing: 419 images (15%)
—Format: COCO JSON
—Resolution: 640x640 pixels

Training Procedure

See mdefrance/signature-detection for details on training procedure.

Metrics

Performances computed on the testing set:

Metric	[yolos-base-signature-detection](https://huggingface.co/mdefrance/yolos-base-signature-detection)	[yolos-small-signature-detection](https://huggingface.co/mdefrance/yolos-small-signature-detection)	[yolos-tiny-signature-detection](https://huggingface.co/mdefrance/yolos-tiny-signature-detection)
Inference Time - CPU (s)	2.250	0.787	0.262
Inference Time - GPU (s)	1.464	0.023	0.014
Parameters	127.73M	30.65M	6.47M
mAP50	0.887	0.859	0.856
mAP50-95	0.495	0.419	0.395

Inference times are computed on a laptop with following specs:

—CPU: Intel Core i7-9750H
—GPU: NVIDIA GeForce GTX 1650

License Comparison

GNU Affero General Public License v3.0 (AGPL-3.0)

AGPL-3.0 is a strong copyleft license designed to keep software and its modifications open-source, especially for web apps and network services.

—Strong Copyleft: Modified versions must also be AGPL-licensed.
—Network Use: Users must get the source code, even if they only interact with the software over a network.
—Commercial Use: Allowed, but any changes must be shared under AGPL-3.0.
—Patent Protection: Includes safeguards against patent and trademark claims.

Apache License 2.0

Apache 2.0 is a permissive license that offers flexibility for both open-source and proprietary use.

—Permissive: Modifications and derivatives don’t need to be open-source.
—Commercial Use: Fully allowed with no requirement to share changes.
—Patent Protection: Includes strong patent clauses.
—Compatibility: Easy to combine with other licenses and projects.

Summary: Why Apache 2.0 Offers More Flexibility

While AGPL-3.0 ensures openness, Apache 2.0 is better suited for businesses and closed-source use:

—No obligation to disclose modified code.
—Easier to integrate into proprietary systems.
—More flexible for commercial applications.

For full license texts, see:

—GNU AGPL-3.0 License
—Apache License 2.0

Citation

This model is a finetuned version of the YOLOS model introduced in the following paper. If you use this model, please cite the original work:

BibTeX:

bibtex

@article{DBLP:journals/corr/abs-2106-00666,
  author    = {Yuxin Fang and
               Bencheng Liao and
               Xinggang Wang and
               Jiemin Fang and
               Jiyang Qi and
               Rui Wu and
               Jianwei Niu and
               Wenyu Liu},
  title     = {You Only Look at One Sequence: Rethinking Transformer in Vision through
               Object Detection},
  journal   = {CoRR},
  volume    = {abs/2106.00666},
  year      = {2021},
  url       = {https://arxiv.org/abs/2106.00666},
  eprinttype = {arXiv},
  eprint    = {2106.00666},
  timestamp = {Fri, 29 Apr 2022 19:49:16 +0200},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2106-00666.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Additional Resources

—Blog post of comparison of Signature Detection Models: Hugging Face Blog
—Blog post associated Finetuning Notebook: Google Colab Notebook
—Finetuning of YOLOS Notebook Example: Google Colab Notebook.ipynb)

Acknowledgements

This model is finetuned for handwritten signature detection using the [tech4humans/signature-detection](https://huggingface.co/datasets/tech4humans/signature-detection) Dataset. The finetuning process and additional resources can be found in the GitHub Repository mdefrance/signature-detection.

Author

<div align="center"> <table> <tr> <td align="center" width="140"> <a href="https://huggingface.co/mdefrance"> <img src="https://avatars.githubusercontent.com/u/74489838?v=4" width="120" alt="Mario DEFRANCE"/> <h3>Mario DEFRANCE</h3> </a> <p><i>Data Scientist / AI Engineer</i></p> </td> <td width="500"> <h4>Responsibilities in this Project</h4> <ul> <li>🔬 Model development and training</li> <li>⚙️ Performance evaluation</li> <li>📝 Technical documentation and model card</li> </ul> </td> </tr> </table> </div>