You Only Look Once v8 Cattle Identification Based on Muzzle Print Pattern Using ORB and Fast Library for Approximate Nearest Neighbor Algorithms

Cattle identification is important in livestock management, and advanced techniques are required to identify cattle without ear tagging, branding, or any identification method that harms the cattle. This study aims to develop computer vision techniques to identify cattle based on their unique muzzle...

Full description

Saved in:
Bibliographic Details
Main Authors: Allan Josef Balderas, Kaila Mae A. Pangilinan, Meo Vincent C. Caya
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Engineering Proceedings
Subjects:
Online Access:https://www.mdpi.com/2673-4591/92/1/53
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849433917999808512
author Allan Josef Balderas
Kaila Mae A. Pangilinan
Meo Vincent C. Caya
author_facet Allan Josef Balderas
Kaila Mae A. Pangilinan
Meo Vincent C. Caya
author_sort Allan Josef Balderas
collection DOAJ
description Cattle identification is important in livestock management, and advanced techniques are required to identify cattle without ear tagging, branding, or any identification method that harms the cattle. This study aims to develop computer vision techniques to identify cattle based on their unique muzzle print features. The developed method employed the YOLOv8 object detection model to detect the cattle’s muzzle. Following detection, the captured muzzle image underwent image processing. Contrast-limited adaptive histogram equalization (CLAHE) was used to enhance the image quality and obtain a prominent and detailed image of the muzzle print. Feature extraction algorithm-oriented FAST and rotated BRIEF (ORB) was applied to extract key points and detect descriptors that are crucial for the cattle identification process. The fast library for approximate nearest neighbor (FLANN) was also employed to identify individual cattle by comparing descriptors of query images from those stored in the database. To validate the developed method, its performance was evaluated on 25 different cattle. In total, 22 out of 25 were correctly identified, resulting in an overall accuracy of 88%.
format Article
id doaj-art-5cd7e7fa4dd94e8bb30f4254a433bd68
institution Kabale University
issn 2673-4591
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Engineering Proceedings
spelling doaj-art-5cd7e7fa4dd94e8bb30f4254a433bd682025-08-20T03:26:52ZengMDPI AGEngineering Proceedings2673-45912025-05-019215310.3390/engproc2025092053You Only Look Once v8 Cattle Identification Based on Muzzle Print Pattern Using ORB and Fast Library for Approximate Nearest Neighbor AlgorithmsAllan Josef Balderas0Kaila Mae A. Pangilinan1Meo Vincent C. Caya2School of Electrical, Electronics and Computer Engineering Mapua University, Manila City 1002, PhilippinesSchool of Electrical, Electronics and Computer Engineering Mapua University, Manila City 1002, PhilippinesSchool of Electrical, Electronics and Computer Engineering Mapua University, Manila City 1002, PhilippinesCattle identification is important in livestock management, and advanced techniques are required to identify cattle without ear tagging, branding, or any identification method that harms the cattle. This study aims to develop computer vision techniques to identify cattle based on their unique muzzle print features. The developed method employed the YOLOv8 object detection model to detect the cattle’s muzzle. Following detection, the captured muzzle image underwent image processing. Contrast-limited adaptive histogram equalization (CLAHE) was used to enhance the image quality and obtain a prominent and detailed image of the muzzle print. Feature extraction algorithm-oriented FAST and rotated BRIEF (ORB) was applied to extract key points and detect descriptors that are crucial for the cattle identification process. The fast library for approximate nearest neighbor (FLANN) was also employed to identify individual cattle by comparing descriptors of query images from those stored in the database. To validate the developed method, its performance was evaluated on 25 different cattle. In total, 22 out of 25 were correctly identified, resulting in an overall accuracy of 88%.https://www.mdpi.com/2673-4591/92/1/53cattle muzzleYOLOv8identificationfeature matchingRaspberry Pi
spellingShingle Allan Josef Balderas
Kaila Mae A. Pangilinan
Meo Vincent C. Caya
You Only Look Once v8 Cattle Identification Based on Muzzle Print Pattern Using ORB and Fast Library for Approximate Nearest Neighbor Algorithms
Engineering Proceedings
cattle muzzle
YOLOv8
identification
feature matching
Raspberry Pi
title You Only Look Once v8 Cattle Identification Based on Muzzle Print Pattern Using ORB and Fast Library for Approximate Nearest Neighbor Algorithms
title_full You Only Look Once v8 Cattle Identification Based on Muzzle Print Pattern Using ORB and Fast Library for Approximate Nearest Neighbor Algorithms
title_fullStr You Only Look Once v8 Cattle Identification Based on Muzzle Print Pattern Using ORB and Fast Library for Approximate Nearest Neighbor Algorithms
title_full_unstemmed You Only Look Once v8 Cattle Identification Based on Muzzle Print Pattern Using ORB and Fast Library for Approximate Nearest Neighbor Algorithms
title_short You Only Look Once v8 Cattle Identification Based on Muzzle Print Pattern Using ORB and Fast Library for Approximate Nearest Neighbor Algorithms
title_sort you only look once v8 cattle identification based on muzzle print pattern using orb and fast library for approximate nearest neighbor algorithms
topic cattle muzzle
YOLOv8
identification
feature matching
Raspberry Pi
url https://www.mdpi.com/2673-4591/92/1/53
work_keys_str_mv AT allanjosefbalderas youonlylookoncev8cattleidentificationbasedonmuzzleprintpatternusingorbandfastlibraryforapproximatenearestneighboralgorithms
AT kailamaeapangilinan youonlylookoncev8cattleidentificationbasedonmuzzleprintpatternusingorbandfastlibraryforapproximatenearestneighboralgorithms
AT meovincentccaya youonlylookoncev8cattleidentificationbasedonmuzzleprintpatternusingorbandfastlibraryforapproximatenearestneighboralgorithms