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

Ultra-Wideband Radar-Based Sensing Poultry Litter Moisture Content Monitoring System.

Animals : an open access journal from MDPI·2026
Same author

Challenges and opportunities: computational biology and the future of agriculture.

Bioinformatics advances·2026
Same author

The Science and Impact of Growth-Enhancing Technologies in Modern Beef Production.

The Veterinary clinics of North America. Food animal practice·2025
Same author

Inclusion of dry or wet fiber plus solubles or high protein distillers grains to replace flint corn, whole cottonseed, and soybean meal in diets for finishing Nellore bulls.

Translational animal science·2025
Same author

Attention-Guided Edge-Optimized Network for Real-Time Detection and Counting of Pre-Weaning Piglets in Farrowing Crates.

Animals : an open access journal from MDPI·2025
Same author

AnimalAI: An Open-Source Web Platform for Automated Animal Activity Index Calculation Using Interactive Deep Learning Segmentation.

Animals : an open access journal from MDPI·2025

Related Experiment Video

Updated: Sep 20, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

543

Individual Beef Cattle Identification Using Muzzle Images and Deep Learning Techniques.

Guoming Li1, Galen E Erickson2, Yijie Xiong2,3

  • 1Department of Agricultural and Biosystems Engineering, Iowa State University, Ames, IA 50011, USA.

Animals : an Open Access Journal From MDPI
|June 10, 2022
PubMed
Summary

Deep learning models can accurately identify individual feedlot beef cattle using muzzle patterns, achieving 98.7% accuracy. This advancement supports precision livestock management and enhances cattle traceability in the food supply chain.

Keywords:
animal biometricscognitive sciencecomputer visionmachine learningpattern recognitionprecision livestock management

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.7K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K

Related Experiment Videos

Last Updated: Sep 20, 2025

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction
06:19

Integration of Animal Behavioral Assessment and Convolutional Neural Network to Study Wasabi-Alcohol Taste-Smell Interaction

Published on: August 16, 2024

543
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.7K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.4K

Area of Science:

  • Agricultural Science
  • Computer Science
  • Animal Science

Background:

  • Individual identification is crucial for beef cattle traceability, disease tracking, and production management.
  • Animal biometric solutions, like muzzle patterns, offer non-invasive identification but require machine learning validation.

Purpose of the Study:

  • To create and release a high-quality dataset of beef cattle muzzle images.
  • To assess and benchmark deep learning models for individual beef cattle recognition.

Main Methods:

  • Collected 4923 muzzle images from 268 US feedlot cattle.
  • Evaluated 59 deep learning image classification models for identification accuracy and speed.

Main Results:

  • Achieved a maximum identification accuracy of 98.7% for individual cattle.
  • The fastest model processed images in 28.3 ms.
  • Weighted cross-entropy and data augmentation improved accuracy with fewer images.

Conclusions:

  • Deep learning shows significant potential for individual cattle identification in precision livestock management.
  • The published dataset can aid further model development for the beef industry.