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: Jul 15, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

12.6K

Deep learning-based double-sided fudge detection system with integrated physical components.

Yuan-Hsun Liao1, Hsiao-Hui Li2

  • 1Department of Computer Science, Tunghai University, Taichung, Taiwan.

Scientific Reports
|April 26, 2026
PubMed
Summary

Related Concept Videos

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...

You might also read

Related Articles

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

Sort by
Same author

Enhanced graph coevolution network for social network analysis using assimilation modified emotional algorithm.

Scientific reports·2026
Same author

Application and effectiveness of adaptive AI in elderly healthcare.

Psychogeriatrics : the official journal of the Japanese Psychogeriatric Society·2024
Same author

An Optimization-Based Technology Applied for Face Skin Symptom Detection.

Healthcare (Basel, Switzerland)·2022
See all related articles

Automated defect detection for fudge production uses deep learning and multiple object detection models. A dual-side inspection system significantly improves accuracy for hole, leak, and white defects in real-time manufacturing.

Area of Science:

  • Food Science and Technology
  • Computer Vision
  • Artificial Intelligence

Background:

  • Manual inspection of food products like fudge is labor-intensive and prone to errors.
  • Existing automated systems may lack the robustness to detect diverse defects effectively.

Purpose of the Study:

  • To develop an automated defect detection system for large-scale fudge production.
  • To enhance defect classification accuracy using a multi-model deep learning approach and dual-side inspection.

Main Methods:

  • Employed deep learning with multiple object detection models (SSD, YOLOv4-v11) for classifying normal and defective fudge samples.
  • Integrated a multi-model strategy with confidence-weighted voting, rule-based selection, and Non-Maximum Suppression (NMS).
  • Implemented a real-time inspection system with a flipping mechanism for dual-side product examination.
Keywords:
Deep learningDefect detectionFood safetyImage recognition

Related Experiment Videos

Last Updated: Jul 15, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

12.6K

Main Results:

  • Initial accuracies for hole, leak, and white defects were 47.5%, 56.7%, and 60.9%.
  • Dual-side inspection boosted accuracies to 75.8% (hole), 83.6% (leak), and 89.3% (white), with hole defects improving by 28.3%.
  • The fusion model achieved 0.995 mAP@0.5 and 0.944 mAP@0.5:0.95, outperforming single models, especially for hole and white defects.

Conclusions:

  • Combining multi-model detection with dual-side inspection significantly enhances defect detection accuracy in fudge production.
  • The developed system offers a reliable solution for real-time quality control in industrial food manufacturing.
  • This approach demonstrates the effectiveness of ensemble methods and comprehensive inspection for improving food product quality assurance.