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 Video

Updated: Dec 11, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K

Efficient Caoshu Character Recognition Scheme and Service Using CNN-Based Recognition Model Optimization.

Boseon Hong1, Bongjae Kim2

  • 1Artificial Intelligence Research Center, Korea Electronics Technology Institute, Seongnam 13488, Korea.

Sensors (Basel, Switzerland)
|August 23, 2020
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

Enhanced Practical Byzantine Fault Tolerance via Dynamic Hierarchy Management and Location-Based Clustering.

Sensors (Basel, Switzerland)ยท2024
See all related articles

This study introduces an optimized Convolutional Neural Network (CNN) model for recognizing Caoshu characters, achieving high accuracy. The developed Caoshu character recognition system performs in real-time via an Android application.

Area of Science:

  • Artificial Intelligence
  • Computer Vision
  • Machine Learning

Background:

  • Deep learning models, particularly Convolutional Neural Networks (CNNs), excel in image recognition tasks.
  • Caoshu, a cursive script, presents significant challenges for automated character recognition due to its complex and fluid nature.

Purpose of the Study:

  • To develop and optimize a CNN-based model for accurate Caoshu character recognition.
  • To enhance the model's performance using image pre-processing and data augmentation techniques.
  • To implement the optimized model as a real-time Android application for Caoshu recognition.

Main Methods:

  • Utilized Convolutional Neural Network (CNN) architecture for character recognition.
  • Applied image pre-processing and data augmentation to a Caoshu dataset.
Keywords:
Caoshu recognitionconvolutional neural networksdata augmentationmobile servicesmodel optimization

More Related Videos

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.5K

Related Experiment Videos

Last Updated: Dec 11, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.8K
Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.5K
  • Trained and validated the optimized CNN model.

    • Main Results:

    • Achieved a TOP-1 recognition accuracy of approximately 98.0% during model validation.
    • The optimized model demonstrated testing performance with accuracy (88.12%), precision (81.84%), recall (84.20%), and F1 score (83.0%).
    • Successfully developed and deployed a real-time Caoshu recognition service on an Android platform.

    Conclusions:

    • The optimized CNN model significantly improves Caoshu character recognition accuracy.
    • The developed Android application provides a practical and efficient solution for real-time Caoshu recognition.
    • The study validates the effectiveness of deep learning techniques in addressing complex character recognition challenges.