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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A hybrid CNN-spectral architecture for non-contact respiratory rate estimation using multi-region optical-flow analysis.

PloS one·2026
Same author

Advanced signal-processing framework for remote photoplethysmography-based heart rate measurement: Integrating adaptive Kalman filtering with discrete wavelet transformation.

PloS one·2026
Same author

A systematic review of contactless respiratory rate measurement using RGB cameras.

Physiological measurement·2025
Same author

<i>S</i>-LIGHT: Synthetic Dataset for the Separation of Diffuse and Specular Reflection Images.

Sensors (Basel, Switzerland)·2024
Same author

FAN-MCCD: Fast and Accurate Network for Multi-Scale Chinese Character Detection.

Sensors (Basel, Switzerland)·2021
Same author

Extremely Robust Remote-Target Detection Based on Carbon Dioxide-Double Spikes in Midwave Spectral Imaging.

Sensors (Basel, Switzerland)·2020

Related Experiment Video

Updated: Aug 8, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.9K

Handwritten Multi-Scale Chinese Character Detector with Blended Region Attention Features and Light-Weighted

Manar Alnaasan1, Sungho Kim1

  • 1Department of Electronics Engineering, Yeungnam University, 280 Daehak-ro, Gyeongsan-si 38541, Republic of Korea.

Sensors (Basel, Switzerland)
|February 28, 2023
PubMed
Summary

A new algorithm, free-candidate multiscale Chinese character detection (FC-MSCCD), accurately locates Chinese characters of various sizes in historical manuscripts. This computer vision method offers a computation-friendly model and outperforms existing state-of-the-art approaches.

Keywords:
blended region attention featureshandwritten Chinese character detectionlight-weighted learning

More Related Videos

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment
05:58

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment

Published on: March 11, 2021

4.6K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

596

Related Experiment Videos

Last Updated: Aug 8, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.9K
Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment
05:58

Digital Handwriting Analysis of Characters in Chinese Patients with Mild Cognitive Impairment

Published on: March 11, 2021

4.6K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

596

Area of Science:

  • Computer Vision
  • Digital Humanities
  • Historical Document Analysis

Background:

  • Character-level detection in historical manuscripts is crucial for recognition but current methods lack precision.
  • Existing techniques struggle with accurately locating characters of varying sizes in historical documents.

Purpose of the Study:

  • To introduce a novel, highly accurate algorithm for character-level detection in historical manuscripts.
  • To develop a computation-friendly model for precise Chinese character localization in old documents.

Main Methods:

  • Developed free-candidate multiscale Chinese character detection (FC-MSCCD) algorithm.
  • Utilized lateral and fusion connections across multiple feature layers.
  • Employed a bottom-up architecture with feature map concatenations.
  • Incorporated a free-candidate detection technique for efficient training.
  • Implemented a proposal-free algorithm for computational friendliness.

Main Results:

  • FC-MSCCD accurately predicts Chinese characters of different sizes in historical documents.
  • The algorithm demonstrates superior performance compared to state-of-the-art detection methods.
  • Achieved high-quality character positioning information through multi-dimensional feature integration.

Conclusions:

  • FC-MSCCD offers a significant advancement in character-level detection for historical manuscripts.
  • The proposed method provides a more accurate and efficient solution for recognizing historical Chinese characters.
  • The algorithm's effectiveness is validated on newly collected benchmark datasets.