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

Targeting mitochondrial ROS in the liver-brain axis attenuates inflammation and oxidative stress in covert hepatic encephalopathy.

Free radical biology & medicine·2026
Same author

An integrated clinicopathological and genomic model for personalized prognosis in stage II-III colorectal cancer: a real-world study.

Frontiers in oncology·2026
Same author

Prevention of immunoglobulin on ventilator-associated pneumonia in critically ill children:a retrospective study.

Respiratory medicine·2025
Same author

The feasibility, safety and short-term clinical efficacy of laparoscopic resection rectopexy with natural orifice specimen extraction surgery for the treatment of complete rectal prolapse.

BMC surgery·2025
Same author

Development of a novel prognostic prediction model using mitochondrial-related genes and single-cell sequencing data for colorectal carcinoma.

Translational gastroenterology and hepatology·2025
Same author

Pediatric trigger thumb treated with A1 pulley release with or without postoperative thumb immobilization: a retrospective study.

Journal of orthopaedic surgery and research·2025
Same journal

The Potential for Bioactive Peptide Production in a Fermented Dairy Beverage Based on Chickpea Water Extract Using Proteolytic Lactic Acid Bacteria.

Foods (Basel, Switzerland)·2026
Same journal

Influence of Protein Concentration on Heat-Induced Fouling of Oat Drink.

Foods (Basel, Switzerland)·2026
Same journal

Microalgae as Future Foods: Unlocking Their Potential and Overcoming Barriers to Market Adoption and Commercialization.

Foods (Basel, Switzerland)·2026
Same journal

Effect of High-Intensity Ultrasound and Calcium Chelation on Functional Properties of Casein Micelles.

Foods (Basel, Switzerland)·2026
Same journal

GC-MS and GC-IMS Based Metabolomics Combined with Cellular Assays to Characterize Volatile Compounds and Pharmacological Activity of <i>Lysimachia foenum-graecum</i> Hance from Different Origins.

Foods (Basel, Switzerland)·2026
Same journal

Research on the Potential Mechanism of Guanine Nucleotides Enhancing the Tolerance of <i>Lactiplantibacillus plantarum</i> Y12.

Foods (Basel, Switzerland)·2026
See all related articles

Related Experiment Video

Updated: Jan 13, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

Computer Vision-Based Deep Learning Modeling for Salmon Part Segmentation and Defect Identification.

Chunxu Zhang1, Yuanshan Zhao2, Wude Yang2

  • 1College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310027, China.

Foods (Basel, Switzerland)
|October 29, 2025
PubMed
Summary
This summary is machine-generated.

A new machine vision system accurately cuts salmon parts and detects defects using a two-stage fusion network. This automated method significantly improves accuracy and efficiency in salmon processing, advancing industrial automation.

Keywords:
defect detectionmachine visionpart segmentationsalmontwo-stage model

More Related Videos

Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish
03:57

Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish

Published on: April 18, 2025

1.0K
Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

13.0K

Related Experiment Videos

Last Updated: Jan 13, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K
Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish
03:57

Anesthesia-free Heartbeat Measurements in Freely Moving Zebrafish

Published on: April 18, 2025

1.0K
Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish
10:56

Long-term Behavioral Tracking of Freely Swimming Weakly Electric Fish

Published on: March 6, 2014

13.0K

Area of Science:

  • Aquaculture Technology
  • Computer Vision
  • Food Processing Automation

Background:

  • Manual inspection of salmon parts and defect detection limits industrial processing efficiency and accuracy.
  • Current methods struggle to meet the demands of large-scale, automated salmon processing.

Purpose of the Study:

  • To develop an automated machine vision inspection method for precise salmon part cutting and defect detection.
  • To enhance the added value of salmon processing through improved accuracy and efficiency.

Main Methods:

  • A visual inspection system was established to collect fish body images, followed by dataset preprocessing and enhancement.
  • An improved U-Net model with a CBAM attention mechanism was used for salmon part segmentation.
  • A two-stage fusion architecture combining YOLOv5 with an improved U-Net was implemented for defect detection and localization.

Main Results:

  • The improved U-Net achieved 96.87% mAP and 94.33% mIoU for part cutting, surpassing the base model.
  • The fusion model for defect detection reached 94.28% mAP with a processing speed of 7.30 fps.
  • The proposed method demonstrated significant improvements in both accuracy (28.02%) and efficiency (236.4%) compared to single U-Net models.

Conclusions:

  • The developed machine vision method offers a high-precision, high-efficiency solution for intelligent salmon processing.
  • This approach significantly advances automation within the aquatic product processing industry.
  • The two-stage fusion network effectively addresses challenges in salmon part cutting and defect recognition.