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

Geometric rectification of camera-captured document images.

Jian Liang1, Daniel DeMenthon, David Doermann

  • 1Amazon.com, 701 5th Avenue #614.B, Seattle, WA 98104, USA. jliang@amazon.com

IEEE Transactions on Pattern Analysis and Machine Intelligence
|February 16, 2008
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

Preoperative Prediction of Esophageal Cancer Survival in CT via Tumor and Lymph Node Context and Geometry Modeling.

IEEE transactions on medical imaging·2026
Same author

Smart mask - Wearable IoT solution for improved protection and personal health.

Internet of things (Amsterdam, Netherlands)·2023
Same author

Racial Disparities in Preterm Birth among Pregnant Women with Obesity.

Southern medical journal·2023
Same author

Risk factors for sepsis in patients with colorectal cancer complicated with gastrointestinal perforation and its impact on prognosis.

Journal of gastrointestinal oncology·2023
Same author

Longevity of centenarians is reflected by the gut microbiome with youth-associated signatures.

Nature aging·2023
Same author

The activities and mechanisms of intestinal microbiota metabolites of TCM herbal ingredients could be illustrated by a strategy integrating spectrum-effects, network pharmacology, metabolomics and molecular docking analysis: Platycodin D as an example.

Phytomedicine : international journal of phytotherapy and phytopharmacology·2023
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

Handheld cameras capture documents easily but cause distortions that hinder optical character recognition (OCR). This study introduces a geometric rectification framework to restore document views, improving OCR accuracy for mobile applications.

Area of Science:

  • Computer Vision
  • Image Processing
  • Document Analysis

Background:

  • Handheld cameras offer portable document capture but introduce distortions (e.g., perspective, non-planar shape).
  • Existing optical character recognition (OCR) technologies often fail with distorted document images.

Purpose of the Study:

  • To present a geometric rectification framework for restoring a frontal-flat view of documents from single camera-captured images.
  • To enable accurate OCR on documents captured by mobile devices.

Main Methods:

  • Estimates 3D document shape using texture flow information directly from the image.
  • Does not require additional 3D/metric data or prior camera calibration.
  • Provides a unified solution for both planar and curved documents.

Related Experiment Videos

Main Results:

  • Successfully restores the frontal-flat view of documents from camera images.
  • Achieves significantly improved OCR compatibility compared to original images.
  • Demonstrates applicability in mobile camera-based document analysis.

Conclusions:

  • The proposed geometric rectification framework effectively corrects distortions in camera-captured documents.
  • This method enhances the usability of mobile devices for document analysis and OCR.
  • It offers a robust solution for various document shapes and capture scenarios.