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

A parallel-line detection algorithm based on HMM decoding.

Yefeng Zheng1, Huiping Li, David Doermann

  • 1Language and Media Processing Laboratory, Institute for Advanced Computer Studies, University of Maryland, College Park, MD 20742-3275, USA. zhengyf@cfar.umd.edu

IEEE Transactions on Pattern Analysis and Machine Intelligence
|May 7, 2005
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

Metabolic reprogramming, oxidative stress, and mitophagy in JSRV Env-transformed BEAS-2B cells: insights from integrated transcriptomics and metabolomics.

BMC genomics·2026
Same author

Clinicopathological discordance and survival outcomes in 154 breast cancer patients with pulmonary metastasis in a real-world setting.

Discover oncology·2026
Same author

Rare 19q13.42 duplication encompassing <i>PRKCG</i> associated with neurodevelopmental abnormalities.

Translational pediatrics·2026
Same author

Abemaciclib in HR+, HER2- Breast Cancer: A Narrative Review of the Clinical Evidence.

Oncology and therapy·2026
Same author

Navigating first- and second-line treatment options in HR+HER2-negative advanced breast cancer.

The oncologist·2026
Same author

Real-world effectiveness of mecapegfilgrastim for prophylaxis in patients with breast cancer receiving 2-weekly and 3-weekly chemotherapy in China.

BMC cancer·2026
Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

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

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

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

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

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

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

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

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

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

Learning Shape Anchors for Holistic Indoor Scene Understanding.

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

This study introduces a new model-based approach using Hidden Markov Models (HMM) for robust parallel line detection in degraded documents. The method effectively extracts lines from challenging documents, outperforming existing techniques.

Area of Science:

  • Computer Vision
  • Document Image Analysis
  • Pattern Recognition

Background:

  • Detecting parallel lines is crucial for form processing and text extraction from ruled documents.
  • Degraded documents with broken lines present significant challenges for traditional line detection methods.

Purpose of the Study:

  • To propose a novel model-based method for robust parallel line detection.
  • To incorporate high-level context into line detection for improved accuracy.
  • To develop a trainable algorithm adaptable to various applications.

Main Methods:

  • Preprocessing includes skew correction and text filtering.
  • Utilizes trained Hidden Markov Models (HMM) for line localization.
  • Employs Viterbi decoding to find optimal line positions on projection profiles.

Related Experiment Videos

Main Results:

  • The proposed method demonstrates robustness in detecting parallel lines.
  • Achieves superior results compared to widely used line detection techniques.
  • Experiments on form processing and rule line detection validate the method's effectiveness.

Conclusions:

  • The novel model-based approach effectively detects parallel lines in challenging, degraded documents.
  • Hidden Markov Models provide a powerful framework for incorporating contextual information.
  • The algorithm's trainability ensures adaptability and broad applicability in document analysis.