On farm automatic sheep breed classification using deep learning

Sanabel Abu Jwade, Andrew Guzzomi, Ajmal Mian

Research output: Contribution to journalArticle

Abstract

Automatic identification of breeds of sheep can be valuable to the sheep industry. Sheep producers need to identify different breeds of sheep to estimate the commercial value of their flock. In many situations however, farmers find it challenging to identify the breeds of sheep without a great deal of experience. DNA testing is an alternative method for breed identification. However, it is not practical for real time assessment of large quantities of sheep in a production environment. Hence, autonomous methods that can efficiently and accurately replicate the identification ability of a sheep breed expert, while operating in a farm environment are beneficial to the industry. Our original contributions in this field include: setting up a prototype computer vision system in a sheep farm, building a database compromising 1642 sheep images of four breeds captured on a farm and labelled by an expert with its breed and training a sheep breed classifier using machine learning and computer vision to achieve an average accuracy of 95.8% with 1.7 standard deviation. This classifier could assist sheep farmers to accurately and efficiently differentiate between breeds and allow more accurate estimation of meat yield and cost management.

Original languageEnglish
Article number105055
JournalComputers and Electronics in Agriculture
Volume167
DOIs
Publication statusPublished - 1 Dec 2019

Fingerprint

sheep breeds
sheep
Farms
Computer vision
Farm buildings
Classifiers
learning
farm
farms
Meats
breeds
computer vision
Learning systems
Industry
DNA
farm buildings
farmers
Testing
artificial intelligence
Costs

Cite this

@article{7814217ada964f7e88044e79ca61180e,
title = "On farm automatic sheep breed classification using deep learning",
abstract = "Automatic identification of breeds of sheep can be valuable to the sheep industry. Sheep producers need to identify different breeds of sheep to estimate the commercial value of their flock. In many situations however, farmers find it challenging to identify the breeds of sheep without a great deal of experience. DNA testing is an alternative method for breed identification. However, it is not practical for real time assessment of large quantities of sheep in a production environment. Hence, autonomous methods that can efficiently and accurately replicate the identification ability of a sheep breed expert, while operating in a farm environment are beneficial to the industry. Our original contributions in this field include: setting up a prototype computer vision system in a sheep farm, building a database compromising 1642 sheep images of four breeds captured on a farm and labelled by an expert with its breed and training a sheep breed classifier using machine learning and computer vision to achieve an average accuracy of 95.8{\%} with 1.7 standard deviation. This classifier could assist sheep farmers to accurately and efficiently differentiate between breeds and allow more accurate estimation of meat yield and cost management.",
keywords = "Agricultural automation, Computer vision, Convolutional neural networks, Deep learning, Image classification, Sheep breed identification",
author = "{Abu Jwade}, Sanabel and Andrew Guzzomi and Ajmal Mian",
year = "2019",
month = "12",
day = "1",
doi = "10.1016/j.compag.2019.105055",
language = "English",
volume = "167",
journal = "Computers and Electronics in Agriculture",
issn = "0168-1699",
publisher = "Elsevier",

}

On farm automatic sheep breed classification using deep learning. / Abu Jwade, Sanabel; Guzzomi, Andrew; Mian, Ajmal.

In: Computers and Electronics in Agriculture, Vol. 167, 105055, 01.12.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - On farm automatic sheep breed classification using deep learning

AU - Abu Jwade, Sanabel

AU - Guzzomi, Andrew

AU - Mian, Ajmal

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Automatic identification of breeds of sheep can be valuable to the sheep industry. Sheep producers need to identify different breeds of sheep to estimate the commercial value of their flock. In many situations however, farmers find it challenging to identify the breeds of sheep without a great deal of experience. DNA testing is an alternative method for breed identification. However, it is not practical for real time assessment of large quantities of sheep in a production environment. Hence, autonomous methods that can efficiently and accurately replicate the identification ability of a sheep breed expert, while operating in a farm environment are beneficial to the industry. Our original contributions in this field include: setting up a prototype computer vision system in a sheep farm, building a database compromising 1642 sheep images of four breeds captured on a farm and labelled by an expert with its breed and training a sheep breed classifier using machine learning and computer vision to achieve an average accuracy of 95.8% with 1.7 standard deviation. This classifier could assist sheep farmers to accurately and efficiently differentiate between breeds and allow more accurate estimation of meat yield and cost management.

AB - Automatic identification of breeds of sheep can be valuable to the sheep industry. Sheep producers need to identify different breeds of sheep to estimate the commercial value of their flock. In many situations however, farmers find it challenging to identify the breeds of sheep without a great deal of experience. DNA testing is an alternative method for breed identification. However, it is not practical for real time assessment of large quantities of sheep in a production environment. Hence, autonomous methods that can efficiently and accurately replicate the identification ability of a sheep breed expert, while operating in a farm environment are beneficial to the industry. Our original contributions in this field include: setting up a prototype computer vision system in a sheep farm, building a database compromising 1642 sheep images of four breeds captured on a farm and labelled by an expert with its breed and training a sheep breed classifier using machine learning and computer vision to achieve an average accuracy of 95.8% with 1.7 standard deviation. This classifier could assist sheep farmers to accurately and efficiently differentiate between breeds and allow more accurate estimation of meat yield and cost management.

KW - Agricultural automation

KW - Computer vision

KW - Convolutional neural networks

KW - Deep learning

KW - Image classification

KW - Sheep breed identification

UR - http://www.scopus.com/inward/record.url?scp=85074210991&partnerID=8YFLogxK

U2 - 10.1016/j.compag.2019.105055

DO - 10.1016/j.compag.2019.105055

M3 - Article

VL - 167

JO - Computers and Electronics in Agriculture

JF - Computers and Electronics in Agriculture

SN - 0168-1699

M1 - 105055

ER -