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: Jun 27, 2026

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

Weakly Supervised Fine-Grained Discrimination of Wheat Mold Using Local RGB-HSI Fusion.

Le Xiao1,2,3, Shengtong Wang1,2,3, Lulu Niu1,2,3

  • 1Key Laboratory of Grain Information Processing and Control, Henan University of Technology, Ministry of Education, Zhengzhou 450001, China.

Foods (Basel, Switzerland)
|June 26, 2026
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

Prefrontal Structural Asymmetry Mediates Body Mass Index and Treatment Response in Major Depressive Disorder.

Depression and anxiety·2026
Same author

Home-based low-field magnetic stimulation as an adjunctive treatment for bipolar depression: A randomized double-blind study.

Journal of affective disorders·2026
Same author

Contribution of Longitudinal Mobile Health Measures in the Dynamic Track of Patients With Major Depressive Disorder: Multiple Centers, Prospective Cohort Study Using Functional Data Analysis and Machine Learning.

JMIR mHealth and uHealth·2026
Same author

m6A Methyltransferase METTL3 Regulates Inflammatory and Immune Microenvironments in Renal Cell Carcinoma via Modulation of the PI3K/AKT Pathway.

International journal of genomics·2026
Same author

Exploring the neural mechanisms of mild cognitive impairment in elderly patients with coronary artery disease using machine learning and source-localized EEG.

Frontiers in neurology·2026
Same author

Effectiveness and Feasibility of Self-Monitoring for Weight Management in Individuals With Mental Disorders Using Digital Intervention: Protocol for a Stepped-Wedge Cluster Randomized Trial ("SWIM" Study).

JMIR research protocols·2026

A new Mask-Guided Fine-Grained Fusion Network accurately assesses mold severity in stored wheat. This weakly supervised framework enhances grain safety and quality by precisely identifying localized mold growth.

Area of Science:

  • Agricultural Science
  • Computer Vision
  • Remote Sensing

Background:

  • Storage mold in wheat threatens grain safety and quality.
  • Existing methods struggle with the subtle, localized nature of mold growth.
  • Fine-grained mold severity grading requires enhanced local feature sensitivity.

Purpose of the Study:

  • To develop a weakly supervised framework for fine-grained, non-destructive mold risk assessment in stored wheat.
  • To improve the sensitivity to local features for accurate mold severity grading.
  • To address limitations of unimodal and global fusion approaches in detecting heterogeneous mold characteristics.

Main Methods:

  • Proposed a Mask-Guided Fine-Grained Fusion Network utilizing local RGB-HSI fusion.
  • Implemented a dynamic A/B experimental design for weakly supervised label generation.
Keywords:
cross-modalfine-grainedmold severityweakly supervisedwheat

Related Experiment Videos

Last Updated: Jun 27, 2026

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

  • Established a preprocessing pipeline for spatial misalignment resolution (single-kernel extraction, segmentation, registration).
  • Incorporated Foreground-Aware Spectral Recalibration (FASR) and Mask-Guided Dilated Cross-modal Local Attention (MDCLA) modules.
  • Utilized a sample-level adaptive fusion strategy for dynamic feature weighting.

    • Main Results:

    • Achieved 0.9689 classification accuracy and 0.9698 Macro-F1 score.
    • Obtained a Mean Absolute Error (MAE) of 0.0593.
    • Significantly outperformed state-of-the-art unimodal deep models and global attention fusion baselines.
    • Demonstrated superior performance in fine-grained mold severity grading.

    Conclusions:

    • The Mask-Guided Fine-Grained Fusion Network provides a robust framework for non-destructive mold risk assessment in stored wheat.
    • Weakly supervised local RGB-HSI fusion effectively captures subtle, heterogeneous mold characteristics.
    • This approach enhances grain safety and quality stability by enabling precise mold detection and grading.