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

Document image binarisation using a supervised neural network.

Adnan Khashman1, Boran Sekeroglu

  • 1Electrical & Electronic Engineering Department, Near East University, Lefkosa, Mersin, Turkey. amk@neu.edu.tr

International Journal of Neural Systems
|November 11, 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

Can epilepsy be predicted after the first febrile seizure? Insights from machine learning of postictal EEG.

Epileptic disorders : international epilepsy journal with videotape·2026
Same author

Sleep Disturbances and Non-REM Phase Alterations in Children with Celiac Disease: A Combined Questionnaire and EEG Study.

Brain sciences·2026
Same author

High-frequency oscillations in autism spectrum disorder: are they related to clinical severity?

Cerebral cortex (New York, N.Y. : 1991)·2025
Same author

Comparative Evaluation of Deep Learning Models for Diagnosis of Helminth Infections.

Journal of personalized medicine·2025
Same author

Detecting emotions through EEG signals based on modified convolutional fuzzy neural network.

Scientific reports·2024
Same author

Focality in childhood absence epilepsy.

Neurological research·2024
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

This study introduces a novel global thresholding method using neural networks for scanned document binarization. The approach effectively separates foreground from background in degraded documents, outperforming local thresholding techniques.

Area of Science:

  • Computer Vision
  • Digital Image Processing
  • Machine Learning

Background:

  • Digital libraries and archives increasingly rely on scanned document images.
  • Degraded scanned documents present challenges like noise, varying contrast, and illumination.
  • Document image binarization is crucial for separating foreground text from background.

Purpose of the Study:

  • To propose a novel global thresholding method for document image binarization.
  • To improve the accuracy and efficiency of binarizing degraded scanned documents.
  • To develop a computationally cost-effective solution compared to existing methods.

Main Methods:

  • A neural network is trained using local threshold values.
  • The trained network determines an optimal global threshold value.

Related Experiment Videos

  • This global threshold is applied to binarize the entire document image.

    • Main Results:

    • The proposed global thresholding method achieves superior binarization results.
    • Experimental comparisons show improved performance over five local thresholding methods.
    • The method is computationally cost-effective for processing degraded documents.

    Conclusions:

    • The novel neural network-based global thresholding method offers an effective solution for degraded document image binarization.
    • This approach provides a computationally efficient and high-performing alternative to traditional local thresholding techniques.
    • The findings contribute to enhancing the quality and accessibility of digitized historical documents.