schliessen

Filtern

 

Bibliotheken

Application of Multispectral Imaging to Determine Quality Attributes and Ripeness Stage in Strawberry Fruit

Multispectral imaging with 19 wavelengths in the range of 405–970 nm has been evaluated for nondestructive determination of firmness, total soluble solids (TSS) content and ripeness stage in strawberry fruit. Several analysis approaches, including partial least squares (PLS), support vector machine... Full description

Journal Title: PLoS One Feb 2014, Vol.9(2), p.e87818
Main Author: Liu, Changhong
Other Authors: Liu, Wei , Lu, Xuzhong , Ma, Fei , Chen, Wei , Yang, Jianbo , Zheng, Lei
Format: Electronic Article Electronic Article
Language: English
Subjects:
ID: E-ISSN: 19326203 ; DOI: 10.1371/journal.pone.0087818
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: proquest1494399985
title: Application of Multispectral Imaging to Determine Quality Attributes and Ripeness Stage in Strawberry Fruit
format: Article
creator:
  • Liu, Changhong
  • Liu, Wei
  • Lu, Xuzhong
  • Ma, Fei
  • Chen, Wei
  • Yang, Jianbo
  • Zheng, Lei
subjects:
  • Fragaria
  • Principal Components Analysis
  • Laboratories
  • Quality Management
  • Classification
  • Nondestructive Testing
  • Models
  • Vision Systems
  • Artificial Neural Networks
  • Firmness
  • Back Propagation Networks
  • Solids
  • Biology
  • Classification
  • Fruits
  • Horticulture
  • Quality
  • Correlation Coefficients
  • Correlation Coefficient
  • Vegetables
  • Model Accuracy
  • Neural Networks
  • Principal Components Analysis
  • Support Vector Machines
  • Technology
  • Classification
  • Imaging
  • Mathematical Models
  • Engineering
  • Fruits
  • Wavelengths
  • Biotechnology
  • Neural Networks
  • Near-Infrared Spectroscopy
  • Fruits
  • Support Vector Machines
  • Neural Networks
  • Principal Component Analysis
  • Forecasting
  • Imaging Techniques
  • Vegetables
ispartof: PLoS One, Feb 2014, Vol.9(2), p.e87818
description: Multispectral imaging with 19 wavelengths in the range of 405–970 nm has been evaluated for nondestructive determination of firmness, total soluble solids (TSS) content and ripeness stage in strawberry fruit. Several analysis approaches, including partial least squares (PLS), support vector machine (SVM) and back propagation neural network (BPNN), were applied to develop theoretical models for predicting the firmness and TSS of intact strawberry fruit. Compared with PLS and SVM, BPNN considerably improved the performance of multispectral imaging for predicting firmness and total soluble solids content with the correlation coefficient (r) of 0.94 and 0.83, SEP of 0.375 and 0.573, and bias of 0.035 and 0.056, respectively. Subsequently, the ability of multispectral imaging technology to classify fruit based on ripeness stage was tested using SVM and principal component analysis-back propagation neural network (PCA-BPNN) models. The higher classification accuracy of 100% was achieved using SVM model. Moreover, the results of all these models demonstrated that the VIS parts of the spectra were the main contributor to the determination of firmness, TSS content estimation and classification of ripeness stage in strawberry fruit. These results suggest that multispectral imaging, together with suitable analysis model, is a promising technology for rapid estimation of quality attributes and classification of ripeness stage in strawberry fruit.
language: eng
source:
identifier: E-ISSN: 19326203 ; DOI: 10.1371/journal.pone.0087818
fulltext: fulltext_linktorsrc
issn:
  • 19326203
  • 1932-6203
url: Link


@attributes
ID826676334
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordid1494399985
sourceidproquest
recordidTN_proquest1494399985
sourcesystemPC
pqid1494399985
galeid478831286
display
typearticle
titleApplication of Multispectral Imaging to Determine Quality Attributes and Ripeness Stage in Strawberry Fruit
creatorLiu, Changhong ; Liu, Wei ; Lu, Xuzhong ; Ma, Fei ; Chen, Wei ; Yang, Jianbo ; Zheng, Lei
ispartofPLoS One, Feb 2014, Vol.9(2), p.e87818
identifierE-ISSN: 19326203 ; DOI: 10.1371/journal.pone.0087818
subjectFragaria ; Principal Components Analysis ; Laboratories ; Quality Management ; Classification ; Nondestructive Testing ; Models ; Vision Systems ; Artificial Neural Networks ; Firmness ; Back Propagation Networks ; Solids ; Biology ; Classification ; Fruits ; Horticulture ; Quality ; Correlation Coefficients ; Correlation Coefficient ; Vegetables ; Model Accuracy ; Neural Networks ; Principal Components Analysis ; Support Vector Machines ; Technology ; Classification ; Imaging ; Mathematical Models ; Engineering ; Fruits ; Wavelengths ; Biotechnology ; Neural Networks ; Near-Infrared Spectroscopy ; Fruits ; Support Vector Machines ; Neural Networks ; Principal Component Analysis ; Forecasting ; Imaging Techniques ; Vegetables
descriptionMultispectral imaging with 19 wavelengths in the range of 405–970 nm has been evaluated for nondestructive determination of firmness, total soluble solids (TSS) content and ripeness stage in strawberry fruit. Several analysis approaches, including partial least squares (PLS), support vector machine (SVM) and back propagation neural network (BPNN), were applied to develop theoretical models for predicting the firmness and TSS of intact strawberry fruit. Compared with PLS and SVM, BPNN considerably improved the performance of multispectral imaging for predicting firmness and total soluble solids content with the correlation coefficient (r) of 0.94 and 0.83, SEP of 0.375 and 0.573, and bias of 0.035 and 0.056, respectively. Subsequently, the ability of multispectral imaging technology to classify fruit based on ripeness stage was tested using SVM and principal component analysis-back propagation neural network (PCA-BPNN) models. The higher classification accuracy of 100% was achieved using SVM model. Moreover, the results of all these models demonstrated that the VIS parts of the spectra were the main contributor to the determination of firmness, TSS content estimation and classification of ripeness stage in strawberry fruit. These results suggest that multispectral imaging, together with suitable analysis model, is a promising technology for rapid estimation of quality attributes and classification of ripeness stage in strawberry fruit.
languageeng
source
version8
oafree_for_read
lds50peer_reviewed
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
linktorsrc$$Uhttp://search.proquest.com/docview/1494399985/?pq-origsite=primo$$EView_record_in_ProQuest_(subscribers_only)
search
creatorcontrib
0Liu, Changhong
1Liu, Wei
2Lu, Xuzhong
3Ma, Fei
4Chen, Wei
5Yang, Jianbo
6Zheng, Lei
titleApplication of Multispectral Imaging to Determine Quality Attributes and Ripeness Stage in Strawberry Fruit
descriptionMultispectral imaging with 19 wavelengths in the range of 405–970 nm has been evaluated for nondestructive determination of firmness, total soluble solids (TSS) content and ripeness stage in strawberry fruit. Several analysis approaches, including partial least squares (PLS), support vector machine (SVM) and back propagation neural network (BPNN), were applied to develop theoretical models for predicting the firmness and TSS of intact strawberry fruit. Compared with PLS and SVM, BPNN considerably improved the performance of multispectral imaging for predicting firmness and total soluble solids content with the correlation coefficient (r) of 0.94 and 0.83, SEP of 0.375 and 0.573, and bias of 0.035 and 0.056, respectively. Subsequently, the ability of multispectral imaging technology to classify fruit based on ripeness stage was tested using SVM and principal component analysis-back propagation neural network (PCA-BPNN) models. The higher classification accuracy of 100% was achieved using SVM model. Moreover, the results of all these models demonstrated that the VIS parts of the spectra were the main contributor to the determination of firmness, TSS content estimation and classification of ripeness stage in strawberry fruit. These results suggest that multispectral imaging, together with suitable analysis model, is a promising technology for rapid estimation of quality attributes and classification of ripeness stage in strawberry fruit.
subject
0Fragaria
1Principal Components Analysis
2Laboratories
3Quality Management
4Classification
5Nondestructive Testing
6Models
7Vision Systems
8Artificial Neural Networks
9Firmness
10Back Propagation Networks
11Solids
12Biology
13Fruits
14Horticulture
15Quality
16Correlation Coefficients
17Correlation Coefficient
18Vegetables
19Model Accuracy
20Neural Networks
21Support Vector Machines
22Technology
23Imaging
24Mathematical Models
25Engineering
26Wavelengths
27Biotechnology
28Near-Infrared Spectroscopy
29Principal Component Analysis
30Forecasting
31Imaging Techniques
32Near-infrared spectroscopy
33Support vector machines
34Neural networks
35Principal component analysis
36Imaging techniques
general
0English
1Public Library of Science
210.1371/journal.pone.0087818
3Medical Database
4Health & Medical Collection (Alumni edition)
5Medical Database (Alumni edition)
6Nursing & Allied Health Database (Alumni edition)
7ProQuest Pharma Collection
8Health & Medical Collection
9Nursing & Allied Health Database
10ProQuest Agriculture Journals
11Ecology Abstracts
12Entomology Abstracts
13Animal Behavior Abstracts
14ProQuest Public Health
15Aquatic Science Journals
16Materials Science Database
17Advanced Technologies & Aerospace Database
18Engineering Database
19Biological Science Database
20Publicly Available Content Database
21Engineering Research Database
22Technology Research Database
23ProQuest Nursing & Allied Health Source
24ProQuest Agricultural Science Collection
25ProQuest Aquatic Science Collection
26ProQuest Atmospheric Science Collection
27ProQuest Biological Science Collection
28ProQuest Central
29ProQuest Earth Science Collection
30ProQuest Engineering Collection
31ProQuest Environmental Science Collection
32ProQuest Advanced Technologies & Aerospace Collection
33ProQuest Hospital Collection
34ProQuest Materials Science Collection
35ProQuest Natural Science Collection
36ProQuest Technology Collection
37Hospital Premium Collection (Alumni edition)
38ProQuest SciTech Collection
39ProQuest Health & Medical Complete
40ProQuest Medical Library
41Agricultural & Environmental Science Database
42Earth, Atmospheric & Aquatic Science Database
43Materials Science & Engineering Database
44Natural Science Collection
45ProQuest Central (new)
46ProQuest Central Korea
47SciTech Premium Collection
48Technology Collection
49Health Research Premium Collection
50Health Research Premium Collection (Alumni edition)
51ProQuest Central Essentials
52ProQuest Central China
sourceidproquest
recordidproquest1494399985
issn
019326203
11932-6203
rsrctypearticle
creationdate2014
addtitlePLoS One
searchscope
01000273
11006072
21006761
31006762
41006763
51006815
61007067
71007107
81007160
91007385
101007396
111007403
121007420
131007431
141007443
151007490
161007515
171007531
181007538
191007617
201007844
211007845
221007849
231007851
241007852
251007853
261007856
271007945
281008886
291008977
301009127
311009240
321009386
3310000002
3410000004
3510000005
3610000006
3710000013
3810000015
3910000020
4010000022
4110000035
4210000036
4310000037
4410000038
4510000039
4610000040
4710000041
4810000043
4910000045
5010000047
5110000049
5210000050
5310000053
5410000117
5510000118
5610000119
5710000120
5810000155
5910000156
6010000157
6110000158
6210000198
6310000200
6410000209
6510000217
6610000233
6710000234
6810000238
6910000244
7010000250
7110000253
7210000255
7310000256
7410000258
7510000260
7610000265
7710000268
7810000270
7910000271
8010000281
8110000300
8210000302
83proquest
scope
01000273
11006072
21006761
31006762
41006763
51006815
61007067
71007107
81007160
91007385
101007396
111007403
121007420
131007431
141007443
151007490
161007515
171007531
181007538
191007617
201007844
211007845
221007849
231007851
241007852
251007853
261007856
271007945
281008886
291008977
301009127
311009240
321009386
3310000002
3410000004
3510000005
3610000006
3710000013
3810000015
3910000020
4010000022
4110000035
4210000036
4310000037
4410000038
4510000039
4610000040
4710000041
4810000043
4910000045
5010000047
5110000049
5210000050
5310000053
5410000117
5510000118
5610000119
5710000120
5810000155
5910000156
6010000157
6110000158
6210000198
6310000200
6410000209
6510000217
6610000233
6710000234
6810000238
6910000244
7010000250
7110000253
7210000255
7310000256
7410000258
7510000260
7610000265
7710000268
7810000270
7910000271
8010000281
8110000300
8210000302
83proquest
lsr43
01000273true
11006072true
21006761true
31006762true
41006763true
51006815true
61007067true
71007107true
81007160true
91007385false
101007396false
111007403false
121007420false
131007431false
141007443false
151007490false
161007515false
171007531false
181007538false
191007617true
201007844true
211007845true
221007849true
231007851true
241007852true
251007853true
261007856true
271007945true
281008886true
291008977true
301009127true
311009240true
321009386true
3310000002false
3410000004false
3510000005false
3610000006false
3710000013false
3810000015false
3910000020true
4010000022false
4110000035true
4210000036true
4310000037true
4410000038true
4510000039true
4610000040true
4710000041true
4810000043true
4910000045true
5010000047true
5110000049true
5210000050true
5310000053true
5410000117true
5510000118true
5610000119true
5710000120true
5810000155true
5910000156true
6010000157true
6110000158true
6210000198false
6310000200false
6410000209false
6510000217false
6610000233true
6710000234true
6810000238true
6910000244true
7010000250true
7110000253true
7210000255true
7310000256true
7410000258true
7510000260true
7610000265true
7710000268true
7810000270true
7910000271true
8010000281true
8110000300true
8210000302true
startdate20140201
enddate20140201
citationpf e87818 vol 9 issue 2
lsr30VSR-Enriched:[galeid, pqid, pages]
sort
titleApplication of Multispectral Imaging to Determine Quality Attributes and Ripeness Stage in Strawberry Fruit
authorLiu, Changhong ; Liu, Wei ; Lu, Xuzhong ; Ma, Fei ; Chen, Wei ; Yang, Jianbo ; Zheng, Lei
creationdate20140201
lso0120140201
facets
frbrgroupid4875128270960979932
frbrtype5
languageeng
creationdate2014
topic
0Fragaria
1Principal Components Analysis
2Laboratories
3Quality Management
4Classification
5Nondestructive Testing
6Models
7Vision Systems
8Artificial Neural Networks
9Firmness
10Back Propagation Networks
11Solids
12Biology
13Fruits
14Horticulture
15Quality
16Correlation Coefficients
17Correlation Coefficient
18Vegetables
19Model Accuracy
20Neural Networks
21Support Vector Machines
22Technology
23Imaging
24Mathematical Models
25Engineering
26Wavelengths
27Biotechnology
28Near-Infrared Spectroscopy
29Principal Component Analysis
30Forecasting
31Imaging Techniques
collection
0Medical Database
1Health & Medical Collection (Alumni edition)
2Medical Database (Alumni edition)
3Nursing & Allied Health Database (Alumni edition)
4ProQuest Pharma Collection
5Health & Medical Collection
6Nursing & Allied Health Database
7ProQuest Agriculture Journals
8Ecology Abstracts
9Entomology Abstracts
10Animal Behavior Abstracts
11ProQuest Public Health
12Aquatic Science Journals
13Materials Science Database
14Advanced Technologies & Aerospace Database
15Engineering Database
16Biological Science Database
17Publicly Available Content Database
18Engineering Research Database
19Technology Research Database
20ProQuest Nursing & Allied Health Source
21ProQuest Agricultural Science Collection
22ProQuest Aquatic Science Collection
23ProQuest Atmospheric Science Collection
24ProQuest Biological Science Collection
25ProQuest Central
26ProQuest Earth Science Collection
27ProQuest Engineering Collection
28ProQuest Environmental Science Collection
29ProQuest Advanced Technologies & Aerospace Collection
30ProQuest Hospital Collection
31ProQuest Materials Science Collection
32ProQuest Natural Science Collection
33ProQuest Technology Collection
34Hospital Premium Collection (Alumni edition)
35ProQuest SciTech Collection
36ProQuest Health & Medical Complete
37ProQuest Medical Library
38Agricultural & Environmental Science Database
39Earth, Atmospheric & Aquatic Science Database
40Materials Science & Engineering Database
41Natural Science Collection
42ProQuest Central (new)
43ProQuest Central Korea
44SciTech Premium Collection
45Technology Collection
46Health Research Premium Collection
47Health Research Premium Collection (Alumni edition)
48ProQuest Central Essentials
49ProQuest Central China
prefilterarticles
rsrctypearticles
creatorcontrib
0Liu, Changhong
1Liu, Wei
2Lu, Xuzhong
3Ma, Fei
4Chen, Wei
5Yang, Jianbo
6Zheng, Lei
jtitlePLoS One
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext_linktorsrc
addata
aulast
0Liu
1Lu
2Ma
3Chen
4Yang
5Zheng
aufirst
0Changhong
1Wei
2Xuzhong
3Fei
4Jianbo
5Lei
au
0Liu, Changhong
1Liu, Wei
2Lu, Xuzhong
3Ma, Fei
4Chen, Wei
5Yang, Jianbo
6Zheng, Lei
atitleApplication of Multispectral Imaging to Determine Quality Attributes and Ripeness Stage in Strawberry Fruit
jtitlePLoS One
risdate20140201
volume9
issue2
spagee87818
eissn19326203
formatjournal
genrearticle
ristypeJOUR
abstractMultispectral imaging with 19 wavelengths in the range of 405–970 nm has been evaluated for nondestructive determination of firmness, total soluble solids (TSS) content and ripeness stage in strawberry fruit. Several analysis approaches, including partial least squares (PLS), support vector machine (SVM) and back propagation neural network (BPNN), were applied to develop theoretical models for predicting the firmness and TSS of intact strawberry fruit. Compared with PLS and SVM, BPNN considerably improved the performance of multispectral imaging for predicting firmness and total soluble solids content with the correlation coefficient (r) of 0.94 and 0.83, SEP of 0.375 and 0.573, and bias of 0.035 and 0.056, respectively. Subsequently, the ability of multispectral imaging technology to classify fruit based on ripeness stage was tested using SVM and principal component analysis-back propagation neural network (PCA-BPNN) models. The higher classification accuracy of 100% was achieved using SVM model. Moreover, the results of all these models demonstrated that the VIS parts of the spectra were the main contributor to the determination of firmness, TSS content estimation and classification of ripeness stage in strawberry fruit. These results suggest that multispectral imaging, together with suitable analysis model, is a promising technology for rapid estimation of quality attributes and classification of ripeness stage in strawberry fruit.
copSan Francisco
pubPublic Library of Science
doi10.1371/journal.pone.0087818
urlhttp://search.proquest.com/docview/1494399985/
pagese87818
oafree_for_read
date2014-02-01