Enhanced CNN for Fruit Disease Detection and Grading Classification Using SSDAE-SVM for Postharvest Fruits

In the realm of agriculture, leveraging image processing has become pivotal for robust image analysis, especially in detecting fruit diseases. However, existing techniques in this domain often limit inputs to fixed sizes without reshaping images before neural network (NN) input, complicating disease...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE sensors journal Jg. 24; H. 5; S. 6719 - 6732
Hauptverfasser: Patel, Himanshu B., Patil, Nitin J.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.03.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:1530-437X, 1558-1748
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In the realm of agriculture, leveraging image processing has become pivotal for robust image analysis, especially in detecting fruit diseases. However, existing techniques in this domain often limit inputs to fixed sizes without reshaping images before neural network (NN) input, complicating disease detection and compromising image resolution, thereby escalating postharvest losses. To address this, an innovative approach has been developed a unique enhanced convolutional NN (CNN) employing spatial pyramid pooling (SPP) and adaptive momentum BP that integrates the best finite impulse response (FIR) filter for preprocessing. This method aims to reorganize the fruit detection process while maintaining high image resolution. The CNN, with its SPP, utilizes convolutional layers to extract diverse features encompassing color, shape, texture, and surface attributes crucial for accurate disease detection. Furthermore, efficient fruit grading is essential to combat issues such as poor product quality, slow grading speeds, and accuracy concerns, all contributing to postharvest losses. In response, a novel integrated stacked sparse denoising autoencoder-support vector machine (SSDAE-SVM) approach, coupled with dropout mechanisms, has been proposed to streamline fruit grading and mitigate postharvest losses. The strategic use of dropout layers mitigates overfitting and information loss during feature extraction, while the SVM classifier, serving as the output layer, ensures accurate fruit grading, thereby curbing postharvest losses. Consequently, this proposed method not only simplifies disease detection and grading processes but also enhances quality, accuracy, reliability, and speed. The model's performance surpasses previous disease prediction models, exhibiting an impressive accuracy of 97.25%, a minimal prediction error of 0.15, a high specificity of 95.62%, an <inline-formula> <tex-math notation="LaTeX">{F}1 </tex-math></inline-formula>-score of 98.81%, and a remarkable recall rate of 98.98%.
AbstractList In the realm of agriculture, leveraging image processing has become pivotal for robust image analysis, especially in detecting fruit diseases. However, existing techniques in this domain often limit inputs to fixed sizes without reshaping images before neural network (NN) input, complicating disease detection and compromising image resolution, thereby escalating postharvest losses. To address this, an innovative approach has been developed a unique enhanced convolutional NN (CNN) employing spatial pyramid pooling (SPP) and adaptive momentum BP that integrates the best finite impulse response (FIR) filter for preprocessing. This method aims to reorganize the fruit detection process while maintaining high image resolution. The CNN, with its SPP, utilizes convolutional layers to extract diverse features encompassing color, shape, texture, and surface attributes crucial for accurate disease detection. Furthermore, efficient fruit grading is essential to combat issues such as poor product quality, slow grading speeds, and accuracy concerns, all contributing to postharvest losses. In response, a novel integrated stacked sparse denoising autoencoder–support vector machine (SSDAE-SVM) approach, coupled with dropout mechanisms, has been proposed to streamline fruit grading and mitigate postharvest losses. The strategic use of dropout layers mitigates overfitting and information loss during feature extraction, while the SVM classifier, serving as the output layer, ensures accurate fruit grading, thereby curbing postharvest losses. Consequently, this proposed method not only simplifies disease detection and grading processes but also enhances quality, accuracy, reliability, and speed. The model’s performance surpasses previous disease prediction models, exhibiting an impressive accuracy of 97.25%, a minimal prediction error of 0.15, a high specificity of 95.62%, an [Formula Omitted]-score of 98.81%, and a remarkable recall rate of 98.98%.
In the realm of agriculture, leveraging image processing has become pivotal for robust image analysis, especially in detecting fruit diseases. However, existing techniques in this domain often limit inputs to fixed sizes without reshaping images before neural network (NN) input, complicating disease detection and compromising image resolution, thereby escalating postharvest losses. To address this, an innovative approach has been developed a unique enhanced convolutional NN (CNN) employing spatial pyramid pooling (SPP) and adaptive momentum BP that integrates the best finite impulse response (FIR) filter for preprocessing. This method aims to reorganize the fruit detection process while maintaining high image resolution. The CNN, with its SPP, utilizes convolutional layers to extract diverse features encompassing color, shape, texture, and surface attributes crucial for accurate disease detection. Furthermore, efficient fruit grading is essential to combat issues such as poor product quality, slow grading speeds, and accuracy concerns, all contributing to postharvest losses. In response, a novel integrated stacked sparse denoising autoencoder-support vector machine (SSDAE-SVM) approach, coupled with dropout mechanisms, has been proposed to streamline fruit grading and mitigate postharvest losses. The strategic use of dropout layers mitigates overfitting and information loss during feature extraction, while the SVM classifier, serving as the output layer, ensures accurate fruit grading, thereby curbing postharvest losses. Consequently, this proposed method not only simplifies disease detection and grading processes but also enhances quality, accuracy, reliability, and speed. The model's performance surpasses previous disease prediction models, exhibiting an impressive accuracy of 97.25%, a minimal prediction error of 0.15, a high specificity of 95.62%, an <inline-formula> <tex-math notation="LaTeX">{F}1 </tex-math></inline-formula>-score of 98.81%, and a remarkable recall rate of 98.98%.
Author Patil, Nitin J.
Patel, Himanshu B.
Author_xml – sequence: 1
  givenname: Himanshu B.
  orcidid: 0000-0002-9994-3126
  surname: Patel
  fullname: Patel, Himanshu B.
  email: himanshu74patel@gmail.com
  organization: D. N. Patel College of Engineering, Shahada, India
– sequence: 2
  givenname: Nitin J.
  surname: Patil
  fullname: Patil, Nitin J.
  email: nitinpatil2002@gmail.com
  organization: D. N. Patel College of Engineering, Shahada, India
BookMark eNp9kE1Lw0AQhhepYK3-AMFDwHPqfiTZ3WNJP1RqFWLFW9huZu2WmtTdVPDfmzQ9iAdPM8y87zvMc456ZVUCQlcEDwnB8vYhmyyGFFM2ZCyigrET1CdxLELCI9Fre4bDiPG3M3Tu_QZjInnM-2gzKdeq1FAE6WIRmMoFU7e3dTC2HpSHYAw16NpWZaDKIpg5VdjyPUi3yntrrFaH1dK3wywbjyZh9vp4iHmufL1W7gt83UX6C3Rq1NbD5bEO0HI6eUnvwvnT7D4dzUNNZVSHvABDtVIJ1loaKTgzKyMKDhywNEKtIsUTkEqoQnOjMdaAQfNiRVkiTETZAN10uTtXfe6b-_mm2ruyOZlTyWjMoygRjYp3Ku0q7x2YXNv68E7tlN3mBOct2LwFm7dg8yPYxkn-OHfOfij3_a_nuvNYAPilZwkXjLAfK9SHGg
CODEN ISJEAZ
CitedBy_id crossref_primary_10_1007_s12530_025_09728_3
Cites_doi 10.4018/IJSSMET.2020040103
10.1016/j.matpr.2020.10.989
10.1007/s11042-019-08564-3
10.1007/s12161-019-01690-6
10.1007/978-981-15-4032-5_83
10.3390/plants10010031
10.1016/j.matpr.2020.12.139
10.1007/s11694-020-00554-6
10.1007/978-981-15-3992-3_40
10.1109/ICECA49313.2020.9297462
10.1111/jfpp.16320
10.14311/NNW.2022.32.019
10.1109/ICECA49313.2020.9297570
10.31838/jcr.07.12.02
10.1088/1742-6596/1881/3/032097
10.1016/j.micpro.2020.103090
10.1007/s41870-022-00860-w
10.3390/info10040129
10.36548/jiip.2020.1.005
10.1002/ima.22406
10.32604/cmc.2022.022809
10.1109/TPDS.2018.2877359
10.1109/Confluence51648.2021.9377186
10.1155/2020/8812019
10.1145/3385414
10.1016/j.compag.2020.105469
10.1109/CVPR42600.2020.00290
10.47760/ijcsmc.2021.v10i08.009
10.1109/CISCE50729.2020.00031
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID 97E
RIA
RIE
AAYXX
CITATION
7SP
7U5
8FD
L7M
DOI 10.1109/JSEN.2023.3342833
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) Online
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList Solid State and Superconductivity Abstracts

Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Geography
Engineering
EISSN 1558-1748
EndPage 6732
ExternalDocumentID 10_1109_JSEN_2023_3342833
10367831
Genre orig-research
GroupedDBID -~X
0R~
29I
4.4
5GY
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACGFS
ACIWK
AENEX
AGQYO
AHBIQ
AJQPL
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
EBS
F5P
HZ~
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
TWZ
AAYXX
CITATION
7SP
7U5
8FD
L7M
ID FETCH-LOGICAL-c294t-7def2caa60cc9f9873fbf8d7e7e09f8ab4a76e9a8adc7fc00ce0ec7db2368f423
IEDL.DBID RIE
ISICitedReferencesCount 2
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001280057500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1530-437X
IngestDate Mon Jun 30 10:02:06 EDT 2025
Tue Nov 18 21:39:25 EST 2025
Sat Nov 29 06:39:50 EST 2025
Wed Aug 27 02:08:38 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 5
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c294t-7def2caa60cc9f9873fbf8d7e7e09f8ab4a76e9a8adc7fc00ce0ec7db2368f423
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-9994-3126
PQID 2932574468
PQPubID 75733
PageCount 14
ParticipantIDs proquest_journals_2932574468
crossref_citationtrail_10_1109_JSEN_2023_3342833
crossref_primary_10_1109_JSEN_2023_3342833
ieee_primary_10367831
PublicationCentury 2000
PublicationDate 2024-03-01
PublicationDateYYYYMMDD 2024-03-01
PublicationDate_xml – month: 03
  year: 2024
  text: 2024-03-01
  day: 01
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE sensors journal
PublicationTitleAbbrev JSEN
PublicationYear 2024
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
Sanjeev (ref3) 2010
ref34
ref15
ref14
ref31
ref11
ref33
ref10
ref2
ref1
ref17
ref16
ref19
ref18
Kumar (ref12) 2020
ref23
ref25
ref20
ref22
ref21
ref28
El-Ghamry (ref32) 2022
ref27
Reddy (ref30) 2022; 4
ref29
ref8
ref7
ref9
ref4
ref6
ref5
Wang (ref24) 2020; 21
Ganguli (ref26) 2022; 2022
References_xml – ident: ref9
  doi: 10.4018/IJSSMET.2020040103
– ident: ref19
  doi: 10.1016/j.matpr.2020.10.989
– ident: ref29
  doi: 10.1007/s11042-019-08564-3
– ident: ref13
  doi: 10.1007/s12161-019-01690-6
– ident: ref5
  doi: 10.1007/978-981-15-4032-5_83
– year: 2022
  ident: ref32
  article-title: In a smart farm, the proposed wireless network IDS can be used to identify attacks by collecting Wi-Fi frames from sensors on framing and watering components and sending them to the suggested IDS
  publication-title: IEEE Sensors J.
– ident: ref7
  doi: 10.3390/plants10010031
– ident: ref27
  doi: 10.1016/j.matpr.2020.12.139
– ident: ref11
  doi: 10.1007/s11694-020-00554-6
– start-page: 477
  year: 2020
  ident: ref12
  article-title: Quality grading of the fruits and vegetables using image processing techniques and machine learning: A review
  publication-title: Advances in Communication Systems and Networks
  doi: 10.1007/978-981-15-3992-3_40
– volume: 4
  issue: 1
  year: 2022
  ident: ref30
  article-title: Deep learning based fruit disease detection
  publication-title: Int. Res. J. Modernization Eng. Technol. Sci.
– ident: ref4
  doi: 10.1109/ICECA49313.2020.9297462
– ident: ref33
  doi: 10.1111/jfpp.16320
– ident: ref15
  doi: 10.14311/NNW.2022.32.019
– ident: ref10
  doi: 10.1109/ICECA49313.2020.9297570
– ident: ref18
  doi: 10.31838/jcr.07.12.02
– ident: ref2
  doi: 10.1088/1742-6596/1881/3/032097
– ident: ref20
  doi: 10.1016/j.micpro.2020.103090
– ident: ref34
  doi: 10.1007/s41870-022-00860-w
– year: 2010
  ident: ref3
  article-title: Image processing useful in agriculture
– volume: 2022
  start-page: 1
  year: 2022
  ident: ref26
  article-title: Deep learning based dual channel banana grading system using convolution neural network
  publication-title: J. Food Qual.
– ident: ref28
  doi: 10.3390/info10040129
– ident: ref17
  doi: 10.36548/jiip.2020.1.005
– ident: ref31
  doi: 10.1002/ima.22406
– ident: ref14
  doi: 10.32604/cmc.2022.022809
– ident: ref23
  doi: 10.1109/TPDS.2018.2877359
– ident: ref6
  doi: 10.1109/Confluence51648.2021.9377186
– ident: ref8
  doi: 10.1155/2020/8812019
– ident: ref25
  doi: 10.1145/3385414
– ident: ref22
  doi: 10.1016/j.compag.2020.105469
– ident: ref1
  doi: 10.1109/CVPR42600.2020.00290
– ident: ref21
  doi: 10.47760/ijcsmc.2021.v10i08.009
– ident: ref16
  doi: 10.1109/CISCE50729.2020.00031
– volume: 21
  start-page: 393
  issue: 2
  year: 2020
  ident: ref24
  article-title: Big data service architecture: A survey
  publication-title: J. Internet Technol.
SSID ssj0019757
Score 2.4040818
Snippet In the realm of agriculture, leveraging image processing has become pivotal for robust image analysis, especially in detecting fruit diseases. However,...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 6719
SubjectTerms Accuracy
Backpropagation (BP) with adaptive momentum
Convolutional neural networks
Disease
Diseases
enhanced convolutional neural network (CNN) with spatial pyramid pooling (SPP)
Feature extraction
FIR filters
Image analysis
Image color analysis
Image processing
Image resolution
Medical imaging
optimum finite impulse response (FIR) Wiener filter
Prediction models
Production
Radio frequency
spatial bin
stacked sparse denoising autoencoder (SSDAE)
support vector machine (SVM)
Support vector machines
Surface layers
Title Enhanced CNN for Fruit Disease Detection and Grading Classification Using SSDAE-SVM for Postharvest Fruits
URI https://ieeexplore.ieee.org/document/10367831
https://www.proquest.com/docview/2932574468
Volume 24
WOSCitedRecordID wos001280057500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVIEE
  databaseName: IEEE Xplore
  customDbUrl:
  eissn: 1558-1748
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0019757
  issn: 1530-437X
  databaseCode: RIE
  dateStart: 20010101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1bS8MwFA46BPXBy1ScTsmDT0Jn2nRN8jh2UUSLMB17K2kubCKddJ3gvzdJuzERBd_6kITSLzk5p-ec7wPgioQaaa6VCXJI5IVRO_U4S4UXGd-BchJFzHW5jh5IHNPxmD1VzequF0Yp5YrPVMs-uly-nImF_VVmTjg2ttV2TW8SEpXNWquUASOO1tOcYOSFmIyrFKaP2M39sB-3rE54C2NLMIa_XUJOVeWHKXb3y2D_n292APYqRxJ2SuQPwYbK6mB3jV6wDrYrhfPJ5xF47WcTl-yH3TiGxlOFg3wxLWCvTNDAnipcUVYGeSbhbe5K66GTzLTFRA4_6OoL4HDY6_S94ejRLWPVfic8t2wd5ZLzY_Ay6D9377xKZ8ETAQsLj0ilA8F5hIRgmlGCdaqpJIooxDTlaWhAU4xTLgXRAiGhkBJEpgGOqDb-2AmoZbNMnQKIVehLYUniJA1lkKaUCeMj-T72RUqCdgOg5YdPREVCbrUw3hIXjCCWWKwSi1VSYdUA16sp7yUDx1-Djy04awNLXBqguYQ3qQ7pPDGejjFYJh6mZ79MOwc7ZvWwrDlrglqRL9QF2BIfxXSeX7r99wVLONd7
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB4hQKI9AKWgbnn50FOlbJ3YG9tHtA8eXaJKS9HeIscP7SIUUDaL1H-P7YQVqKJSbznYTpQvMx5nZr4P4BujFltpjTvksDSiaa-IpChUlLrYgUuWpiJ0ud6OWZbx6VT8apvVQy-MMSYUn5muvwy5fP2glv5XmbNw4nyr75re6FGa4KZda5U0ECwQezobxhElbNomMWMsflxNhlnXK4V3CfEUY-TNNhR0Vf5yxmGHGe3857PtwnYbSqKzBvtPsGbKPfj4imBwD7ZajfPZn89wNyxnId2P-lmGXKyKRtVyXqNBk6JBA1OHsqwSyVKj8yoU16MgmunLiQKCKFQYoMlkcDaMJrfXYRmv9zuTlefraJZc7MPv0fCmfxG1SguRSgStI6aNTZSUKVZKWMEZsYXlmhlmsLBcFtTBZoTkUitmFcbKYKOYLhKScusisgNYLx9K8wUQMTTWytPEaU51UhRcKBclxTGJVcGSXgfwy4vPVUtD7tUw7vNwHMEi91jlHqu8xaoD31dTHhsOjn8N3vfgvBrY4NKBoxd489ZMF7mLdZzLcidi_vWdaaewdXFzPc7Hl9nPQ_jg7kSbCrQjWK-rpTmGTfVUzxfVSfgWnwGoP9rC
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Enhanced+CNN+for+Fruit+Disease+Detection+and+Grading+Classification+Using+SSDAE-SVM+for+Postharvest+Fruits&rft.jtitle=IEEE+sensors+journal&rft.au=Patel%2C+Himanshu+B.&rft.au=Patil%2C+Nitin+J.&rft.date=2024-03-01&rft.pub=IEEE&rft.issn=1530-437X&rft.volume=24&rft.issue=5&rft.spage=6719&rft.epage=6732&rft_id=info:doi/10.1109%2FJSEN.2023.3342833&rft.externalDocID=10367831
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-437X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-437X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-437X&client=summon