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

Text extraction and document image segmentation using matched wavelets and MRF model.

Sunil Kumar1, Rajat Gupta, Nitin Khanna

  • 1IBM India Research Laboratory, Delhi-110 016, India. sunil_narang@rediffmail.com

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
|August 11, 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

Bilateral symmetrically symptomatic cervical Hirayama disease diagnosed with dynamic magnetic resonance imaging.

Surgical neurology international·2026
Same author

Refining Aesthetics and Volume: A Retrospective Analysis of Our Experience With Autoaugmentation Mastopexy.

Annals of plastic surgery·2026
Same author

Enhancing Cleavage Aesthetics in Patients Seeking Breast Augmentation: Surgical Technique and Key Considerations.

Indian journal of plastic surgery : official publication of the Association of Plastic Surgeons of India·2026
Same author

Co-Creation of a Study Protocol to Assess the Effect of Transcranial Direct Current Stimulation in the Management of Fatigue in Children and Young People With Acquired Brain Injury (Fatiguebrain-tDCS).

Health expectations : an international journal of public participation in health care and health policy·2026
Same author

Public Awareness as a Tool for Improving Community Health: A Systematic Review of Communication and Community-Based Interventions.

Cureus·2026
Same author

Heat-related deaths in social care in England: can the Care Quality Commission ratings system be used to identify care homes that would benefit most from heat adaptation measures?

Age and ageing·2026

This study introduces a new method for extracting text from images using wavelet filters and clustering. The approach effectively segments document images into text, background, and picture components.

Area of Science:

  • Image processing
  • Computer vision
  • Pattern recognition

Background:

  • Accurate text extraction and image segmentation are crucial for document analysis.
  • Existing methods may struggle with complex image layouts and varying text characteristics.

Purpose of the Study:

  • To propose a novel scheme for extracting textual regions from images.
  • To extend the scheme for segmenting document images into text, background, and picture components.
  • To enhance segmentation accuracy using contextual information.

Main Methods:

  • Utilized globally matched wavelet filters for text extraction.
  • Employed a clustering-based technique to estimate these filters using groundtruth images.
  • Applied multiple two-class Fisher classifiers for component segmentation.

Related Experiment Videos

  • Incorporated a Markov random field (MRF) formulation for pixel labeling and refinement.

    • Main Results:

    • The proposed scheme effectively extracts textual areas from images.
    • Successful segmentation of document images into text, background, and picture categories.
    • Refinement using MRF improved segmentation accuracy.

    Conclusions:

    • The developed method provides an effective approach for image text extraction and document image segmentation.
    • The combination of wavelet filters, clustering, Fisher classifiers, and MRF offers robust performance.