schliessen

Filtern

 

Bibliotheken

Broiler weight estimation based on machine vision and artificial neural network

1. Machine vision and artificial neural network (ANN) procedures were used to estimate live body weight of broiler chickens in 30 1-d-old broiler chickens reared for 42 d. 2. Imaging was performed two times daily. To localise chickens within the pen, an ellipse fitting algorithm was used and the chi... Full description

Journal Title: British poultry science April 2017, Vol.58(2), pp.200-205
Main Author: Amraei, S
Other Authors: Abdanan Mehdizadeh, S , Salari, S
Format: Electronic Article Electronic Article
Language: English
Subjects:
Quelle: MEDLINE/PubMed (U.S. National Library of Medicine)
ID: E-ISSN: 1466-1799 ; PMID: 27845565 Version:1 ; DOI: 10.1080/00071668.2016.1259530
Link: http://pubmed.gov/27845565
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: medline27845565
title: Broiler weight estimation based on machine vision and artificial neural network
format: Article
creator:
  • Amraei, S
  • Abdanan Mehdizadeh, S
  • Salari, S
subjects:
  • Machine Vision
  • Artificial Neural Network
  • Body Weight
  • Broiler
  • Body Weight
  • Neural Networks (Computer)
  • Animal Husbandry -- Methods
  • Chickens -- Physiology
ispartof: British poultry science, April 2017, Vol.58(2), pp.200-205
description: 1. Machine vision and artificial neural network (ANN) procedures were used to estimate live body weight of broiler chickens in 30 1-d-old broiler chickens reared for 42 d. 2. Imaging was performed two times daily. To localise chickens within the pen, an ellipse fitting algorithm was used and the chickens' head and tail removed using the Chan-Vese method. 3. The correlations between the body weight and 6 physical extracted features indicated that there were strong correlations between body weight and the 5 features including area, perimeter, convex area, major and minor axis length. 5. According to statistical analysis there was no significant difference between morning and afternoon data over 42 d. 6. In an attempt to improve the accuracy of live weight approximation different ANN techniques, including Bayesian regulation, Levenberg-Marquardt, Scaled conjugate gradient and gradient descent were used. Bayesian regulation with R value of 0.98 was the best network for prediction of broiler weight. 7. The accuracy of the machine vision technique was examined and most errors were less than 50 g.
language: eng
source: MEDLINE/PubMed (U.S. National Library of Medicine)
identifier: E-ISSN: 1466-1799 ; PMID: 27845565 Version:1 ; DOI: 10.1080/00071668.2016.1259530
fulltext: fulltext
issn:
  • 14661799
  • 1466-1799
url: Link


@attributes
ID1822037159
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordid27845565
sourceidmedline
recordidTN_medline27845565
sourceformatXML
sourcesystemOther
display
typearticle
titleBroiler weight estimation based on machine vision and artificial neural network
creatorAmraei, S ; Abdanan Mehdizadeh, S ; Salari, S
ispartofBritish poultry science, April 2017, Vol.58(2), pp.200-205
identifier
subjectMachine Vision ; Artificial Neural Network ; Body Weight ; Broiler ; Body Weight ; Neural Networks (Computer) ; Animal Husbandry -- Methods ; Chickens -- Physiology
description1. Machine vision and artificial neural network (ANN) procedures were used to estimate live body weight of broiler chickens in 30 1-d-old broiler chickens reared for 42 d. 2. Imaging was performed two times daily. To localise chickens within the pen, an ellipse fitting algorithm was used and the chickens' head and tail removed using the Chan-Vese method. 3. The correlations between the body weight and 6 physical extracted features indicated that there were strong correlations between body weight and the 5 features including area, perimeter, convex area, major and minor axis length. 5. According to statistical analysis there was no significant difference between morning and afternoon data over 42 d. 6. In an attempt to improve the accuracy of live weight approximation different ANN techniques, including Bayesian regulation, Levenberg-Marquardt, Scaled conjugate gradient and gradient descent were used. Bayesian regulation with R value of 0.98 was the best network for prediction of broiler weight. 7. The accuracy of the machine vision technique was examined and most errors were less than 50 g.
languageeng
sourceMEDLINE/PubMed (U.S. National Library of Medicine)
lds50peer_reviewed
links
openurl$$Topenurl_article
backlink$$Uhttp://pubmed.gov/27845565$$EView_this_record_in_MEDLINE/PubMed
openurlfulltext$$Topenurlfull_article
addlink$$Uhttp://exlibris-pub.s3.amazonaws.com/aboutMedline.html$$EView_the_MEDLINE/PubMed_Copyright_Statement
search
creatorcontrib
0Amraei, S
1Abdanan Mehdizadeh, S
2Salari, S
titleBroiler weight estimation based on machine vision and artificial neural network
description1. Machine vision and artificial neural network (ANN) procedures were used to estimate live body weight of broiler chickens in 30 1-d-old broiler chickens reared for 42 d. 2. Imaging was performed two times daily. To localise chickens within the pen, an ellipse fitting algorithm was used and the chickens' head and tail removed using the Chan-Vese method. 3. The correlations between the body weight and 6 physical extracted features indicated that there were strong correlations between body weight and the 5 features including area, perimeter, convex area, major and minor axis length. 5. According to statistical analysis there was no significant difference between morning and afternoon data over 42 d. 6. In an attempt to improve the accuracy of live weight approximation different ANN techniques, including Bayesian regulation, Levenberg-Marquardt, Scaled conjugate gradient and gradient descent were used. Bayesian regulation with R value of 0.98 was the best network for prediction of broiler weight. 7. The accuracy of the machine vision technique was examined and most errors were less than 50 g.
subject
0Machine Vision
1Artificial Neural Network
2Body Weight
3Broiler
4Neural Networks (Computer)
5Animal Husbandry -- Methods
6Chickens -- Physiology
general
027845565
1English
2MEDLINE/PubMed (U.S. National Library of Medicine)
310.1080/00071668.2016.1259530
4MEDLINE/PubMed (NLM)
sourceidmedline
recordidmedline27845565
issn
014661799
11466-1799
rsrctypearticle
creationdate2017
addtitleBritish poultry science
searchscope
0medline
1nlm_medline
2MEDLINE
scope
0medline
1nlm_medline
2MEDLINE
lsr41201704
citationpf 200 vol 58 issue 2
startdate20170401
enddate20170431
sort
titleBroiler weight estimation based on machine vision and artificial neural network
authorAmraei, S ; Abdanan Mehdizadeh, S ; Salari, S
creationdate20170400
lso0120170400
facets
frbrgroupid6660228919362306131
frbrtype6
newrecords20190701
languageeng
creationdate2017
topic
0Machine Vision
1Artificial Neural Network
2Body Weight
3Broiler
4Neural Networks (Computer)
5Animal Husbandry–Methods
6Chickens–Physiology
collectionMEDLINE/PubMed (NLM)
prefilterarticles
rsrctypearticles
creatorcontrib
0Amraei, S
1Abdanan Mehdizadeh, S
2Salari, S
jtitleBritish Poultry Science
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
aulast
0Amraei
1Abdanan Mehdizadeh
2Salari
aufirstS
au
0Amraei, S
1Abdanan Mehdizadeh, S
2Salari, S
atitleBroiler weight estimation based on machine vision and artificial neural network
jtitleBritish poultry science
risdate201704
volume58
issue2
spage200
pages200-205
eissn1466-1799
formatjournal
genrearticle
ristypeJOUR
abstract1. Machine vision and artificial neural network (ANN) procedures were used to estimate live body weight of broiler chickens in 30 1-d-old broiler chickens reared for 42 d. 2. Imaging was performed two times daily. To localise chickens within the pen, an ellipse fitting algorithm was used and the chickens' head and tail removed using the Chan-Vese method. 3. The correlations between the body weight and 6 physical extracted features indicated that there were strong correlations between body weight and the 5 features including area, perimeter, convex area, major and minor axis length. 5. According to statistical analysis there was no significant difference between morning and afternoon data over 42 d. 6. In an attempt to improve the accuracy of live weight approximation different ANN techniques, including Bayesian regulation, Levenberg-Marquardt, Scaled conjugate gradient and gradient descent were used. Bayesian regulation with R value of 0.98 was the best network for prediction of broiler weight. 7. The accuracy of the machine vision technique was examined and most errors were less than 50 g.
doi10.1080/00071668.2016.1259530
pmid27845565
oafree_for_read
date2017-04