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 Experiment Videos

Restoring 2D content from distorted documents.

Michael S Brown1, Mingxuan Sun, Ruigang Yang

  • 1School of Computer Engineering, Nanyang Technological University, Blk N4, 2A-32, Nanyang Avenue, Singapore 639798, Republic of Singapore. msbrown@ntu.edu.sg

IEEE Transactions on Pattern Analysis and Machine Intelligence
|September 13, 2007
PubMed
Summary
This summary is machine-generated.

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

The chromosome-level genome assembly of Malus robusta (Rosales: Rosaceae).

Scientific data·2026
Same author

A Framework for Cross-Domain Generalization in Coronary Artery Calcium Scoring Across Gated and Non-Gated Computed Tomography.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same author

Ink detection from surface topography of the Herculaneum papyri.

Scientific reports·2026
Same author

Leveraging Color Naming for Image Enhancement.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Sunitinib induces immunogenic cell death through eIF2α phosphorylation to potentiate immunotherapy in HCC.

iScience·2026
Same author

Bio-inspired fractal-structured gel-drugs enable enhancing deep tumor penetration for efficient chemotherapy of hepatocellular carcinoma.

Journal of controlled release : official journal of the Controlled Release Society·2026
Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads.

IEEE transactions on pattern analysis and machine intelligence·2026
Same journal

Achieving Text-based Person Retrieval with Any Granularity.

IEEE transactions on pattern analysis and machine intelligence·2026
See all related articles

This study introduces a framework to restore 2D document content distorted by geometry and illumination. It accurately reconstructs original non-textual document appearances, preserving details lost in standard imaging methods.

Area of Science:

  • Computer Vision
  • Image Processing
  • Document Analysis

Background:

  • Traditional document imaging often focuses on text readability or OCR, neglecting the preservation of original non-textual content.
  • Geometric distortion and non-uniform illumination are significant challenges in accurately restoring printed documents.

Purpose of the Study:

  • To present a novel framework for restoring 2D content on documents affected by geometric distortion and non-uniform illumination.
  • To recover the original printed appearance of non-textual documents, going beyond text-based restoration methods.

Main Methods:

  • Acquiring a 3D scan of the document surface alongside a high-resolution image.
  • Employing conformal mapping for geometric distortion correction (deskewing) without assuming a parametric surface model.

Related Experiment Videos

  • Utilizing 3D shape information to differentiate content and illumination gradients for photometric correction.

    • Main Results:

    • Successfully rectified arbitrary geometric distortions by mapping the 3D surface back to a plane with minimized angular distortion.
    • Significantly reduced illumination artifacts in the final reflectance image by integrating content edges.
    • Combined geometric and photometric corrections to produce a restored 2D document image.

    Conclusions:

    • The proposed framework effectively restores 2D document content under challenging geometric and illumination conditions.
    • This method is particularly valuable for non-textual documents where preserving the original visual fidelity is paramount.
    • The approach is robust, making no assumptions about document surface models or lighting conditions.