What does the Stamp Verification Dataset include?

The dataset includes 400 scanned invoice images at 200 dpi with varying stamp shapes, colors, and orientations. Ground truth includes binary maps for stamp regions, pixel-level masks, and metadata such as signature presence, text overlap, stamp count, and stamp color.

What are the applications of the Stamp Verification Dataset?

It supports the development of automated systems for stamp segmentation, verification, and document processing in industries such as insurance and finance, where large-scale document authentication is required.

What makes stamp detection challenging in this dataset?

Stamps vary in shape, color, quality, and orientation, and may overlap with printed text or signatures. Some documents contain multiple stamps or none at all, making detection and segmentation tasks non-trivial.

Stamp Verification Dataset

Home » Dataset Download » Stamp Verification Dataset

Stamp Verification Dataset

Datasets

File

Stamp Verification

Use Case

Stamp Verification

Description

Explore our comprehensive Stamp Verification Dataset featuring 400 scanned invoice images with varying stamp shapes, colors, and orientations.

Description:

The dataset addresses the need for an automated system for stamp segmentation and verification, particularly for environments like insurance companies where a large volume of documents is processed daily. Stamps can vary in shape, color, quality, and orientation, making detection challenging. This dataset aids researchers in developing such systems.

Download Dataset

Content:

The dataset includes 400 scanned document images of automatically generated invoices, printed, stamped, and scanned at 200 dpi resolution. Documents contain color logos and texts, and stamps of various shapes and colors, some overlapping with signatures or text. Some documents have multiple stamps or none. Ground truth is provided as binary images with stamp stroke masks for pixel-wise evaluation.

Folders include:

Scans: Stamped genuine document scans.
Ground-truth-maps: Maps defining stamp regions.
Ground-truth-pixel: Pixel-level ground truth.
Info: Text files with information for each file, including:
- Signature [0|1]: Signature presence.
- TextOverlap [0|1]: Stamp overlap with printed text.
- NumStamps [0|…|n]: Number of stamps.
- BwStamp [1|…|n]: Stamp color (black or colored).

Key Features of the Dataset

High-quality scanned document images
Pixel-level ground truth annotations
Multiple stamp shapes and colors
Documents with overlapping text and signatures
Suitable for segmentation and verification tasks

Applications and Use Cases

The Stamp Segmentation and Verification Dataset can be used in several important areas. For example:

Document Verification Systems: Detect and verify official stamps
Insurance Automation: Process large volumes of documents efficiently
Optical Character Recognition (OCR): Improve document understanding
Computer Vision Research: Train segmentation and detection models

Conclusion

The Stamp Segmentation and Verification Dataset is a valuable resource for document analysis and automation research. Overall, it provides diverse scanned documents and detailed annotations for accurate stamp detection. More importantly, it helps improve automated verification systems across real-world business applications.

This dataset is sourced from Kaggle.

Contact Us

Let's Discuss your Data collection Requirement With Us

To get a detailed estimation of requirements please reach us.

Stamp Verification Dataset