Back to articles
Regular Article FastTrack
Volume: 0 | Article ID: 050502
Image
Seal2Real: Prompt Prior Learning on Diffusion Model for Unsupervised Document Seal Data Generation and Realization
Abstract
Abstract

Seal-related tasks in document processing—such as seal segmentation, authenticity verification, seal removal, and text recognition under seals—hold substantial commercial importance. However, progress in these areas has been hindered by the scarcity of labeled document seal datasets, which are essential for supervised learning. To address this limitation, we propose Seal2Real, a novel generative framework designed to synthesize large-scale labeled document seal data. As part of this work, we also present Seal-DB, a comprehensive dataset containing 20,000 labeled images to support seal-related research. Seal2Real introduces a prompt prior learning architecture built upon a pretrained Stable Diffusion model, effectively transferring its generative capability to the unsupervised domain of seal image synthesis. By producing highly realistic synthetic seal images, Seal2Real significantly enhances the performance of downstream seal-related tasks on real-world data. Experimental evaluations on the Seal-DB dataset demonstrate the effectiveness and practical value of the proposed framework.

Subject Areas :
Views 0
Downloads 0
 articleview.views 0
 articleview.downloads 0
  Cite this article 

Mingfu Yan, Jiancheng Huang, Shifeng Chen, "Seal2Real: Prompt Prior Learning on Diffusion Model for Unsupervised Document Seal Data Generation and Realizationin Journal of Imaging Science and Technology,  2025,  pp 1 - 11,  https://doi.org/10.2352/J.ImagingSci.Technol.2025.69.5.050502

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2025
  Article timeline 
  • received April 2025
  • accepted May 2025

Preprint submitted to:
  Login or subscribe to view the content