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

Online handwritten shape recognition using segmental hidden Markov models.

Thierry Artières1, Sanparith Marukatat, Patrick Gallinari

  • 1LIP6, Université Paris, France. Thierry.artieres@lip6.fr

IEEE Transactions on Pattern Analysis and Machine Intelligence
|December 16, 2006
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

Reconstructing voice identity from noninvasive auditory cortex recordings.

eLife·2026
Same author

Insights on Scan-Specific Deep-Learning Strategies for Brain MRI Parallel Imaging Reconstruction.

NMR in biomedicine·2025
Same author

A large annotated dataset of vocalizations by common marmosets.

Scientific data·2025
Same author

Machine learning models for predicting hepatocellular carcinoma development in patients with chronic viral hepatitis B infection.

Asian biomedicine : research, reviews and news·2025
Same author

Exhaled volatile organic compounds for cholangiocarcinoma diagnosis.

Liver research·2025
Same author

Artificial intelligence for ultrasonographic detection and diagnosis of hepatocellular carcinoma and cholangiocarcinoma.

Scientific reports·2024

This study introduces a novel online handwritten shape recognition system. It learns efficiently from minimal data, adapts to users, and recognizes diverse 2D shapes like characters and gestures.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Online handwritten shape recognition is crucial for human-computer interaction.
  • Existing systems often require extensive training data and manual parameter tuning.
  • Adaptability to user-specific needs and incremental learning remain challenges.

Purpose of the Study:

  • To develop a novel online handwritten shape recognition system.
  • To enable efficient learning from limited training samples.
  • To facilitate incremental learning and user adaptation for diverse graphical shapes.

Main Methods:

  • A new machine learning approach for online handwritten shape recognition.
  • Features include automated learning without manual tuning.

Related Experiment Videos

  • The system supports incremental learning and user-specific adaptation.

    • Main Results:

    • The proposed system effectively recognizes various 2D graphical shapes.
    • Demonstrates learning from very few training samples.
    • Achieves adaptation to user-specific requirements.

    Conclusions:

    • The developed system offers a flexible and efficient solution for online handwritten shape recognition.
    • It serves as a foundational component for various recognition tasks.
    • Potential applications span character recognition, gesture recognition, and symbol recognition.