Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

DynamicVLN: Incorporating Dynamics into Vision-and-Language Navigation Scenarios.

Sensors (Basel, Switzerland)·2025
Same author

A Comprehensive Analysis of a Social Intelligence Dataset and Response Tendencies Between Large Language Models (LLMs) and Humans.

Sensors (Basel, Switzerland)·2025
Same author

RetinaViT: Efficient Visual Backbone for Online Video Streams.

Sensors (Basel, Switzerland)·2024
Same author

Proto-Adapter: Efficient Training-Free CLIP-Adapter for Few-Shot Image Classification.

Sensors (Basel, Switzerland)·2024
Same author

Action Quality Assessment Model Using Specialists' Gaze Location and Kinematics Data-Focusing on Evaluating Figure Skating Jumps.

Sensors (Basel, Switzerland)·2023
Same author

Boosting Semantic Segmentation by Conditioning the Backbone with Semantic Boundaries.

Sensors (Basel, Switzerland)·2023

Related Experiment Video

Updated: Jul 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

542

Synthetic Document Images with Diverse Shadows for Deep Shadow Removal Networks.

Yuhi Matsuo1, Yoshimitsu Aoki1

  • 1Department of Electrical Engineering, Faculty of Science and Technology, Keio University, 3-14-1 Hiyoshi, Kohoku-ku, Yokohama 223-8522, Kanagawa, Japan.

Sensors (Basel, Switzerland)
|January 26, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces the SynDocDS dataset and the Dual Shadow Fusion Network (DSFN) for improved document shadow removal. Training on SynDocDS enhances performance, boosting metrics like PSNR and SSIM for better digitized document applications.

Keywords:
deep neural networksdocument imagesshadow removal

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

Related Experiment Videos

Last Updated: Jul 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

542
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

Area of Science:

  • Computer Vision
  • Digital Image Processing
  • Machine Learning

Background:

  • Document shadow removal is crucial for digitized documents.
  • Existing methods struggle with limited diverse datasets and synthetic data limitations.
  • Synthesized datasets often lack document diversity and varied lighting conditions.

Purpose of the Study:

  • Introduce a large-scale, diverse Synthetic Document with Diverse Shadows (SynDocDS) dataset.
  • Propose a Dual Shadow Fusion Network (DSFN) for robust document shadow removal.
  • Enhance deep shadow removal network performance using diverse synthetic data.

Main Methods:

  • Developed the SynDocDS dataset using a physics-based illumination model for diverse shadow rendering.
  • Proposed the Dual Shadow Fusion Network (DSFN) with high global color comprehension.
  • Trained and evaluated models on SynDocDS and public datasets (OSR, Kligler's, Jung's).

Main Results:

  • Training on SynDocDS improved average PSNR from 23.00 dB to 25.70 dB and SSIM from 0.959 to 0.971.
  • The proposed DSFN outperformed existing networks on multiple metrics (PSNR, SSIM).
  • Demonstrated significant improvements in Optical Character Recognition (OCR) performance post-shadow removal.

Conclusions:

  • The SynDocDS dataset enables training of more robust and high-performance shadow removal networks.
  • DSFN effectively handles document-specific color features for superior shadow removal.
  • The proposed approach significantly advances document image digitization quality and usability.