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

Hydrogen peroxide redistributes the localization of protein phosphatase methylesterase 1.

Life sciences·2018
Same author

Environmental triggers of a Microcystis (Cyanophyceae) bloom in an artificial lagoon of Hangzhou Bay, China.

Marine pollution bulletin·2018
Same author

Quantitative evaluation of retinal artery occlusion using optical coherence tomography angiography: A case report.

Medicine·2018
Same author

Multibandgap quantum dot ensembles for solar-matched infrared energy harvesting.

Nature communications·2018
Same author

Butylamine-Catalyzed Synthesis of Nanocrystal Inks Enables Efficient Infrared CQD Solar Cells.

Advanced materials (Deerfield Beach, Fla.)·2018
Same author

A secretory hexokinase plays an active role in the proliferation of <i>Nosema bombycis</i>.

PeerJ·2018

Related Experiment Video

Updated: Mar 8, 2026

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
07:15

Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

Published on: July 11, 2025

3.4K

Blind Bleed-Through Removal for Scanned Historical Document Image With Conditional Random Fields.

Bin Sun, Shutao Li, Xiao-Ping Zhang

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |January 24, 2017
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel blind method using conditional random fields (CRFs) to effectively remove ink bleed-through from scanned historical documents. The technique preserves foreground content while accurately eliminating bleed-through artifacts.

    More Related Videos

    High-plex Imaging using Spectral Confocal Microscopy to Minimize Non-specific Tissue Fluorescence
    10:28

    High-plex Imaging using Spectral Confocal Microscopy to Minimize Non-specific Tissue Fluorescence

    Published on: October 28, 2025

    682
    In Vivo Vascular Injury Readouts in Mouse Retina to Promote Reproducibility
    07:35

    In Vivo Vascular Injury Readouts in Mouse Retina to Promote Reproducibility

    Published on: April 21, 2022

    2.7K

    Related Experiment Videos

    Last Updated: Mar 8, 2026

    Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging
    07:15

    Transient Optical Clearing Using Absorbing Molecules for Ex Vivo and In Vivo Imaging

    Published on: July 11, 2025

    3.4K
    High-plex Imaging using Spectral Confocal Microscopy to Minimize Non-specific Tissue Fluorescence
    10:28

    High-plex Imaging using Spectral Confocal Microscopy to Minimize Non-specific Tissue Fluorescence

    Published on: October 28, 2025

    682
    In Vivo Vascular Injury Readouts in Mouse Retina to Promote Reproducibility
    07:35

    In Vivo Vascular Injury Readouts in Mouse Retina to Promote Reproducibility

    Published on: April 21, 2022

    2.7K

    Area of Science:

    • Digital image processing
    • Historical document preservation
    • Computer vision

    Background:

    • Scanned historical documents often exhibit bleed-through, obscuring original content.
    • Existing methods may require multiple scans or manual intervention.
    • Bleed-through is a common artifact in digitizing fragile historical materials.

    Purpose of the Study:

    • To develop a blind method for removing bleed-through from single-sided scanned historical document images.
    • To accurately segment and remove the bleed-through component while preserving foreground information.
    • To improve the legibility and archival quality of digitized historical documents.

    Main Methods:

    • A conditional random field (CRF) based approach is proposed.
    • Gaussian distributions model foreground, bleed-through, and background components.
    • Conditional probability distribution (CPD) models are established and parameters estimated.
    • Belief propagation algorithm calculates pixel label probabilities.
    • Random-filling inpainting removes the identified bleed-through component.

    Main Results:

    • The proposed method effectively removes bleed-through artifacts.
    • Foreground components of historical documents are well-preserved.
    • Experimental results demonstrate high performance on real datasets.
    • The blind approach eliminates the need for multiple scans.

    Conclusions:

    • The CRF-based method offers an effective solution for bleed-through removal in historical document images.
    • This technique enhances the quality and accessibility of digitized historical archives.
    • The blind nature of the method simplifies the digitization workflow.