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 predictive model for early neurological deterioration in medullary infarction based on explainable machine learning.

The International journal of neuroscience·2026
Same author

<i>Cryptococcus gattii</i> meningitis with a pulmonary cryptococcoma and cerebrospinal fluid epstein-barr virus reactivation: A diagnostic challenge.

IDCases·2026
Same author

Early proteomic and metabolomic signatures in diabetes associated with progression to diabetic retinopathy over 1-2 years.

Frontiers in endocrinology·2026
Same author

Molecular characterization of thioredoxin peroxidases 1 from Trichinella spiralis and its potential in generating protective immunity.

Parasites & vectors·2026
Same author

Gut microbiome components predict response to neoadjuvant short-course radiotherapy followed by camrelizumab and chemotherapy in locally advanced rectal cancer (UNION): a prospective study.

Frontiers in pharmacology·2026
Same author

CO<sub>2</sub> Reduction and Urea Synthesis on Dual-Atom Catalysts: Toward the Synthesis of C<sub>1</sub>, C<sub>2</sub>, and C<sub>2+</sub> Products and Urea.

ChemSusChem·2026

Related Experiment Video

Updated: Jul 7, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.4K

Image completion algorithm of anthurium spathes based on multi-scale feature learning.

Hongyu Wei1, Jiahui Li1, Wenyue Chen1

  • 1College of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou, China.

Frontiers in Plant Science
|December 28, 2023
PubMed
Summary
This summary is machine-generated.

This study introduces a new multi-scale fusion Recurrent Feature Reasoning (RFR) network to repair incomplete anthurium spathe images. The advanced RFR network effectively handles large missing areas, improving machine vision grading accuracy in plant production.

Keywords:
deep learningimage completionmulti-scalepotted anthuriumvisualization

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

405
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

743

Related Experiment Videos

Last Updated: Jul 7, 2025

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
08:47

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

1.4K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

405
Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility
07:46

Author Spotlight: Revolutionizing Remote Surgery with Augmented Reality and Robotics for Enhanced Precision and Accessibility

Published on: August 9, 2024

743

Area of Science:

  • Computer Vision
  • Agricultural Technology
  • Image Processing

Background:

  • Machine vision is increasingly used for grading potted anthurium plants in large-scale production.
  • Current methods face accuracy limitations due to occlusion and incomplete spathe images caused by shooting angle limitations.
  • Traditional image completion models struggle with repairing large missing areas in spathe images.

Purpose of the Study:

  • To develop an improved image completion method for repairing incomplete anthurium spathe images, particularly those with large missing areas.
  • To enhance the accuracy of machine vision systems used in anthurium plant grading.
  • To address the limitations of traditional image completion techniques in agricultural applications.

Main Methods:

  • A novel multi-scale fusion Recurrent Feature Reasoning (RFR) network was proposed.
  • The network incorporates a multi-layer component in its feature reasoning module to combine multi-scale features.
  • A comparative experiment was conducted against widely used image completion networks.

Main Results:

  • The proposed multi-scale fusion RFR network demonstrated superior performance in image completion tasks compared to traditional methods.
  • The network showed particular effectiveness in repairing spathe images with large missing areas.
  • The enhanced network successfully captured more spathe details, leading to improved completion accuracy across various scenarios.

Conclusions:

  • The multi-scale fusion RFR network offers a significant advancement for image completion in machine vision applications, especially in agriculture.
  • This method effectively overcomes the limitations of existing models in handling large-area image inpainting.
  • The improved image completion accuracy contributes to more reliable machine vision-based grading of anthurium plants.