Introduction #
Authors introduce SignverOD: A Dataset Signature Object Detection, a curated dataset of 2576 scanned document images with 7103 bounding box annotations, across 4 categories (signature, initials, redaction, date). SignverOD cover a diverse set of document types including memos, emails, bank cheques, lease agreements and letters, memos, invoices. Detecting the presence and location of hand written artifacts such as signatures, dates, initials can be critical for scanned (offline) document processing systems. This capability can support multiple downstream tasks such as signature verification, document tagging and categorization.
Please note that this is the updated version of the dataset, with an increased number of original images.
Dataset Source
Images of documents in this dataset are sourced from 4 main locations and then annotated:
Tobacco800 is a publicly accessible document image collection with realistic scope and complexity is important to the document image analysis and search community.
The NIST.gov structured Forms Database consists of 5,590 pages of binary, black-and-white images of synthesized documents. The documents in this database are 12 different tax forms from the IRS 1040 Package X for the year 1988.
The bank cheques dataset is a collection of xx colored images of bank checks. They consist of scanned realistic checks as well as examplar signatures with signatures.
GSA provides electronic copies of GSA lease documents for general public viewing. The lease documents are sorted by region and contain, for the most part, GSA Lease Forms and Lease Amendments (LA) from selected GSA leases across the nation.
Please note that we have removed duplicate photos from the test split
Expand
Homepage
Blog Post
GitHubSummary #
SignverOD: A Dataset Signature Object Detection is a dataset for an object detection task. Possible applications of the dataset could be in the optical character recognition (OCR) domain and security industry.
The dataset consists of 2765 images with 8022 labeled objects belonging to 4 different classes including signature, initials, redaction, and other: date.
Images in the SignverOD dataset have bounding box annotations. All images are labeled (i.e. with annotations). There are 2 splits in the dataset: train (2565 images) and test (200 images). The dataset was released in 2021.
Explore #
SignverOD dataset has 2765 images. Click on one of the examples below or open "Explore" tool anytime you need to view dataset images with annotations. This tool has extended visualization capabilities like zoom, translation, objects table, custom filters and more. Hover the mouse over the images to hide or show annotations.
Class balance #
There are 4 annotation classes in the dataset. Find the general statistics and balances for every class in the table below. Click any row to preview images that have labels of the selected class. Sort by column to find the most rare or prevalent classes.
Class ã…¤ | Images ã…¤ | Objects ã…¤ | Count on image average | Area on image average |
|---|---|---|---|---|
signatureâž” rectangle | 2242 | 4551 | 2.03 | 2.93% |
initialsâž” rectangle | 524 | 989 | 1.89 | 0.72% |
redactionâž” rectangle | 396 | 1912 | 4.83 | 1.42% |
dateâž” rectangle | 376 | 570 | 1.52 | 0.74% |
Co-occurrence matrix #
Co-occurrence matrix is an extremely valuable tool that shows you the images for every pair of classes: how many images have objects of both classes at the same time. If you click any cell, you will see those images. We added the tooltip with an explanation for every cell for your convenience, just hover the mouse over a cell to preview the description.
Images #
Explore every single image in the dataset with respect to the number of annotations of each class it has. Click a row to preview selected image. Sort by any column to find anomalies and edge cases. Use horizontal scroll if the table has many columns for a large number of classes in the dataset.
Object distribution #
Interactive heatmap chart for every class with object distribution shows how many images are in the dataset with a certain number of objects of a specific class. Users can click cell and see the list of all corresponding images.
Class sizes #
The table below gives various size properties of objects for every class. Click a row to see the image with annotations of the selected class. Sort columns to find classes with the smallest or largest objects or understand the size differences between classes.
Class | Object count | Avg area | Max area | Min area | Min height | Min height | Max height | Max height | Avg height | Avg height | Min width | Min width | Max width | Max width |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
signature rectangle | 4551 | 1.47% | 13.14% | 0% | 44px | 0.99% | 664px | 41.87% | 178px | 5.39% | 2px | 0.06% | 2369px | 69.47% |
redaction rectangle | 1912 | 0.3% | 13.59% | 0.03% | 47px | 1.07% | 816px | 18.48% | 99px | 2.25% | 71px | 1.67% | 2788px | 78.67% |
initials rectangle | 989 | 0.38% | 1.61% | 0.06% | 62px | 1.41% | 497px | 11.3% | 222px | 5.04% | 90px | 2.64% | 1141px | 33.56% |
date rectangle | 570 | 0.49% | 2.63% | 0.1% | 65px | 1.46% | 357px | 8.13% | 157px | 3.56% | 137px | 4.02% | 1293px | 37.67% |
Spatial Heatmap #
The heatmaps below give the spatial distributions of all objects for every class. These visualizations provide insights into the most probable and rare object locations on the image. It helps analyze objects' placements in a dataset.
Objects #
Table contains all 8022 objects. Click a row to preview an image with annotations, and use search or pagination to navigate. Sort columns to find outliers in the dataset.
Object ID ã…¤ | Class ã…¤ | Image name click row to open | Image size height x width | Height ã…¤ | Height ã…¤ | Width ã…¤ | Width ã…¤ | Area ã…¤ |
|---|---|---|---|---|---|---|---|---|
1âž” | signature rectangle | gsa_LAL61027-SLA-3-_Z-01.png | 4390 x 3424 | 231px | 5.26% | 556px | 16.24% | 0.85% |
2âž” | signature rectangle | gsa_LAL61027-SLA-3-_Z-01.png | 4390 x 3424 | 321px | 7.31% | 1400px | 40.89% | 2.99% |
3âž” | date rectangle | gsa_LAL61027-SLA-3-_Z-01.png | 4390 x 3424 | 148px | 3.37% | 555px | 16.21% | 0.55% |
4âž” | initials rectangle | gsa_LAL61971-Lease_Z-04.png | 4402 x 3440 | 291px | 6.61% | 229px | 6.66% | 0.44% |
5âž” | initials rectangle | gsa_LAL61971-Lease_Z-04.png | 4402 x 3440 | 199px | 4.52% | 208px | 6.05% | 0.27% |
6âž” | redaction rectangle | gsa_LAL61971-Lease_Z-04.png | 4402 x 3440 | 73px | 1.66% | 543px | 15.78% | 0.26% |
7âž” | redaction rectangle | gsa_LAL61971-Lease_Z-04.png | 4402 x 3440 | 62px | 1.41% | 412px | 11.98% | 0.17% |
8âž” | redaction rectangle | gsa_LAL61971-Lease_Z-04.png | 4402 x 3440 | 59px | 1.34% | 546px | 15.87% | 0.21% |
9âž” | redaction rectangle | gsa_LAL61971-Lease_Z-04.png | 4402 x 3440 | 65px | 1.48% | 233px | 6.77% | 0.1% |
10âž” | redaction rectangle | gsa_LAL61971-Lease_Z-04.png | 4402 x 3440 | 115px | 2.61% | 324px | 9.42% | 0.25% |
License #
Citation #
If you make use of the SignverOD data, please cite the following reference:
@article{DibiaReed2022signverod,
author = {Victor, Dibia},
title = {A Dataset for Handwritten Signature ObjectDetection in Scanned Documents.},
year = {2022},
publisher = {victordibia.com},
journal = {victordibia.com},
url = {https://victordibia.com/signverod.pdf}
}
@article{Dibia2022signver,
author = {Victor, Dibia and Andrew Reed},
title = {SignVer: A Deep Learning Library for Automatic Offline Signature Verification Tasks},
year = {2022},
publisher = {victordibia.com},
journal = {victordibia.com},
url = {https://victordibia.com/signver.pdf}
}
If you are happy with Dataset Ninja and use provided visualizations and tools in your work, please cite us:
@misc{ visualization-tools-for-signver-od-dataset,
title = { Visualization Tools for SignverOD Dataset },
type = { Computer Vision Tools },
author = { Dataset Ninja },
howpublished = { \url{ https://datasetninja.com/signver-od } },
url = { https://datasetninja.com/signver-od },
journal = { Dataset Ninja },
publisher = { Dataset Ninja },
year = { 2024 },
month = { jul },
note = { visited on 2024-07-27 },
}Download #
Dataset SignverOD can be downloaded in Supervisely format:
As an alternative, it can be downloaded with dataset-tools package:
pip install --upgrade dataset-tools
… using following python code:
import dataset_tools as dtools
dtools.download(dataset='SignverOD', dst_dir='~/dataset-ninja/')
Make sure not to overlook the python code example available on the Supervisely Developer Portal. It will give you a clear idea of how to effortlessly work with the downloaded dataset.
The data in original format can be downloaded here.
Disclaimer #
Our gal from the legal dep told us we need to post this:
Dataset Ninja provides visualizations and statistics for some datasets that can be found online and can be downloaded by general audience. Dataset Ninja is not a dataset hosting platform and can only be used for informational purposes. The platform does not claim any rights for the original content, including images, videos, annotations and descriptions. Joint publishing is prohibited.
You take full responsibility when you use datasets presented at Dataset Ninja, as well as other information, including visualizations and statistics we provide. You are in charge of compliance with any dataset license and all other permissions. You are required to navigate datasets homepage and make sure that you can use it. In case of any questions, get in touch with us at hello@datasetninja.com.