Lychee cultivar fine-grained image classification method based on improved ResNet-34 residual network
Lychee, a key economic crop in southern China, has numerous similar-looking varieties. Classifying these can aid farmers in understanding each variety's growth and market demand, enhancing agricultural efficiency. However, existing classification techniques are subjective, complex, and costly....
Saved in:
Published in | Journal of agricultural engineering (Pisa, Italy) Vol. 55; no. 3 |
---|---|
Main Authors | , , , , , , , , , |
Format | Journal Article |
Language | English |
Published |
Bologna
PAGEPress Publications
01.01.2024
|
Subjects | |
Online Access | Get full text |
ISSN | 1974-7071 2239-6268 |
DOI | 10.4081/jae.2024.1593 |
Cover
Abstract | Lychee, a key economic crop in southern China, has numerous similar-looking varieties. Classifying these can aid farmers in understanding each variety's growth and market demand, enhancing agricultural efficiency. However, existing classification techniques are subjective, complex, and costly. This paper proposes a lychee classification method using an improved ResNet-34 residual network for six common varieties. We enhance the CBAM attention mechanism by replacing the large receptive field in the SAM module with a smaller one. Attention mechanisms are added at key network stages, focusing on crucial image information. Transfer learning is employed to apply ImageNet-trained model weights to this task. Test set evaluations demonstrate that our improved ResNet-34 network surpasses the original, achieving a recognition accuracy of 95.8442%, a 5.58 percentage point improvement. |
---|---|
AbstractList | Lychee, a key economic crop in southern China, has numerous similar-looking varieties. Classifying these can aid farmers in understanding each variety's growth and market demand, enhancing agricultural efficiency. However, existing classification techniques are subjective, complex, and costly. This paper proposes a lychee classification method using an improved ResNet-34 residual network for six common varieties. We enhance the CBAM attention mechanism by replacing the large receptive field in the SAM module with a smaller one. Attention mechanisms are added at key network stages, focusing on crucial image information. Transfer learning is employed to apply ImageNet-trained model weights to this task. Test set evaluations demonstrate that our improved ResNet-34 network surpasses the original, achieving a recognition accuracy of 95.8442%, a 5.58 percentage point improvement. Lychee, a key economic crop in southern Chi, has numerous similar-looking varieties. Classifying these can aid farmers in understanding each variety's growth and market demand, enhancing agricultural efficiency. However, existing classification techniques are subjective, complex, and costly. This paper proposes a lychee classification method using an improved ResNet-34 residual network for six common varieties. We enhance the CBAM attention mechanism by replacing the large receptive field in the SAM module with a smaller one. Attention mechanisms are added at key network stages, focusing on crucial image information. Transfer learning is employed to apply ImageNet-trained model weights to this task. Test set evaluations demonstrate that our improved ResNet-34 network surpasses the origil, achieving a recognition accuracy of 95.8442%, a 5.58 percentage point improvement. |
Author | Long, Yongbin Wang, Jianhua Xiong, Hongyi Xiao, Fangjun Wu, Bofei Huang, Renhuan Zhou, Jinfeng Lan, Yubin Xiao, Yiming Hong, Licong |
Author_xml | – sequence: 1 givenname: Yiming surname: Xiao fullname: Xiao, Yiming – sequence: 2 givenname: Jianhua surname: Wang fullname: Wang, Jianhua – sequence: 3 givenname: Hongyi surname: Xiong fullname: Xiong, Hongyi – sequence: 4 givenname: Fangjun surname: Xiao fullname: Xiao, Fangjun – sequence: 5 givenname: Renhuan surname: Huang fullname: Huang, Renhuan – sequence: 6 givenname: Licong surname: Hong fullname: Hong, Licong – sequence: 7 givenname: Bofei surname: Wu fullname: Wu, Bofei – sequence: 8 givenname: Jinfeng surname: Zhou fullname: Zhou, Jinfeng – sequence: 9 givenname: Yongbin surname: Long fullname: Long, Yongbin – sequence: 10 givenname: Yubin surname: Lan fullname: Lan, Yubin |
BookMark | eNo9UU1LJDEQDaLgrHr03rDnHvPV-Tgu4q7CoCDeQ3VSPWbs6WjS4-K_N-OIp_p69aoe7xc5ntKEhFwyupTUsKsN4JJTLpess-KILDgXtlVcmWOyYFbLVlPNTslFKRtKKePWaisWBFcf_hmx8btxju-QmyFO2K4z1BCauIV1nY1QShyihzmmqdni_JxC00OpiFrH7WtO7zV_xHKPcytkk7HEsIOxmXD-n_LLOTkZYCx48R3PyNPfm6fr23b18O_u-s-q9YKruR2EQq2Yp6YPTFsl-k5prqHrBw3Wdwwl16bz3AZjMQAwpUynejnoqqcXZ-TuQBsSbNxrru_nD5cguq9GymsHeY5-RMeplFpwo5EZaUWwtLfKCgkCAg_GV67fB64q7m2HZXabtMtT_d4JVje5FVZUVHtA-ZxKyTj8XGXU7X1x1Re398XtfRGftH6BLA |
Cites_doi | 10.1109/TKDE.2009.191 10.32604/cmc.2022.028334 10.1016/j.foodchem.2012.09.085 10.1016/j.autcon.2022.104734 10.1016/j.est.2023.106812 10.3390/molecules26041181 10.1109/CVPR.2016.319 10.1016/j.compag.2022.107119 10.1007/s11295-012-0560-1 10.1007/s11783-023-1677-1 10.1016/j.bspc.2023.104652 10.1007/s12161-014-9826-6 10.1016/j.engappai.2023.105899 10.1016/0304-4238(95)00788-U 10.1007/s00371-018-1582-y 10.1016/j.compag.2023.107622 10.1016/j.neucom.2023.01.087 10.1079/9780851996967.0059 10.1371/journal.pone.0135390 10.1007/978-981-10-3644-6_2 10.1016/j.compbiomed.2023.106726 10.1016/j.dt.2021.02.005 10.1039/D1FO01148K 10.1016/j.jisa.2018.03.009 10.1016/j.eswa.2023.119614 10.1007/s00521-022-07793-2 10.17660/ActaHortic.2010.863.1 10.3389/fpls.2022.1066115 10.1016/j.scienta.2020.109360 10.1016/j.compag.2022.106805 10.1109/CVPR52688.2022.00714 10.1007/978-3-030-01234-2_1 10.1016/j.compbiomed.2023.106575 10.1016/j.neucom.2021.01.042 10.1016/j.compind.2023.103872 10.1016/j.compbiomed.2022.106496 |
ContentType | Journal Article |
Copyright | 2024. This work is licensed under https://creativecommons.org/licenses/by-nc/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2024. This work is licensed under https://creativecommons.org/licenses/by-nc/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | AAYXX CITATION 3V. 7X2 8FE 8FG 8FH 8FK ABJCF ABUWG AEUYN AFKRA ATCPS AZQEC BENPR BGLVJ BHPHI CCPQU DWQXO HCIFZ L6V M0K M7S PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PTHSS DOA |
DOI | 10.4081/jae.2024.1593 |
DatabaseName | CrossRef ProQuest Central (Corporate) Agricultural Science Collection ProQuest SciTech Collection ProQuest Technology Collection ProQuest Natural Science Collection ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Materials Science & Engineering ProQuest Central (Alumni) ProQuest One Sustainability (subscription) ProQuest Central UK/Ireland Agricultural & Environmental Science Collection ProQuest Central Essentials ProQuest Central Technology Collection Natural Science Collection ProQuest One ProQuest Central Korea SciTech Premium Collection ProQuest Engineering Collection Agricultural Science Database Engineering Database (ProQuest) ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database (ProQuest) ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic ProQuest One Academic UKI Edition Engineering Collection DOAJ Directory of Open Access Journals |
DatabaseTitle | CrossRef Agricultural Science Database Publicly Available Content Database Technology Collection ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Natural Science Collection ProQuest Central ProQuest One Applied & Life Sciences ProQuest One Sustainability ProQuest Engineering Collection Natural Science Collection ProQuest Central Korea Agricultural & Environmental Science Collection ProQuest Central (New) Engineering Collection Engineering Database ProQuest One Academic Eastern Edition Agricultural Science Collection ProQuest Technology Collection ProQuest SciTech Collection ProQuest One Academic UKI Edition Materials Science & Engineering Collection ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) |
DatabaseTitleList | CrossRef Agricultural Science Database |
Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Agriculture |
EISSN | 2239-6268 |
ExternalDocumentID | oai_doaj_org_article_204473287e18493d90b96934a3ad2d8c 10_4081_jae_2024_1593 |
GroupedDBID | 5VS 67V 7X2 AAYXX ABDBF ABJCF ACUHS ADBBV AEUYN AFKRA ALMA_UNASSIGNED_HOLDINGS ATCPS BCNDV BENPR BGLVJ BHPHI CCPQU CITATION GROUPED_DOAJ HCIFZ KQ8 M0K M7S PHGZM PHGZT PIMPY PTHSS 3V. 8FE 8FG 8FH 8FK ABUWG AZQEC DWQXO L6V PKEHL PQEST PQGLB PQQKQ PQUKI PUEGO |
ID | FETCH-LOGICAL-c326t-f36e761c08bd17963b56727a5bf7a9c51e42785c29d89edaa166856b4f7299b3 |
IEDL.DBID | 8FG |
ISSN | 1974-7071 |
IngestDate | Wed Aug 27 01:29:55 EDT 2025 Fri Jul 25 11:55:25 EDT 2025 Tue Jul 01 02:21:48 EDT 2025 |
IsDoiOpenAccess | true |
IsOpenAccess | true |
IsPeerReviewed | true |
IsScholarly | true |
Issue | 3 |
Language | English |
License | https://creativecommons.org/licenses/by-nc/4.0 |
LinkModel | DirectLink |
MergedId | FETCHMERGED-LOGICAL-c326t-f36e761c08bd17963b56727a5bf7a9c51e42785c29d89edaa166856b4f7299b3 |
Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
OpenAccessLink | https://www.proquest.com/docview/3173229393?pq-origsite=%requestingapplication% |
PQID | 3173229393 |
PQPubID | 4728908 |
ParticipantIDs | doaj_primary_oai_doaj_org_article_204473287e18493d90b96934a3ad2d8c proquest_journals_3173229393 crossref_primary_10_4081_jae_2024_1593 |
ProviderPackageCode | CITATION AAYXX |
PublicationCentury | 2000 |
PublicationDate | 2024-01-01 |
PublicationDateYYYYMMDD | 2024-01-01 |
PublicationDate_xml | – month: 01 year: 2024 text: 2024-01-01 day: 01 |
PublicationDecade | 2020 |
PublicationPlace | Bologna |
PublicationPlace_xml | – name: Bologna |
PublicationTitle | Journal of agricultural engineering (Pisa, Italy) |
PublicationYear | 2024 |
Publisher | PAGEPress Publications |
Publisher_xml | – name: PAGEPress Publications |
References | 17068 17069 17064 17086 17065 17087 17066 17088 17067 17089 17060 17082 17061 17083 17062 17084 17063 17085 17080 17081 17079 17058 17059 17075 17097 17076 17098 17077 17078 17071 17093 17072 17094 17073 17095 17074 17096 17090 17091 17070 17092 |
References_xml | – ident: 17080 doi: 10.1109/TKDE.2009.191 – ident: 17081 doi: 10.32604/cmc.2022.028334 – ident: 17095 doi: 10.1016/j.foodchem.2012.09.085 – ident: 17094 doi: 10.1016/j.autcon.2022.104734 – ident: 17098 doi: 10.1016/j.est.2023.106812 – ident: 17068 doi: 10.3390/molecules26041181 – ident: 17069 – ident: 17062 doi: 10.1109/CVPR.2016.319 – ident: 17082 doi: 10.1016/j.compag.2022.107119 – ident: 17076 doi: 10.1007/s11295-012-0560-1 – ident: 17071 doi: 10.1007/s11783-023-1677-1 – ident: 17090 doi: 10.1016/j.bspc.2023.104652 – ident: 17074 doi: 10.1007/s12161-014-9826-6 – ident: 17058 doi: 10.1016/j.engappai.2023.105899 – ident: 17065 – ident: 17061 doi: 10.1016/0304-4238(95)00788-U – ident: 17063 – ident: 17072 doi: 10.1007/s00371-018-1582-y – ident: 17088 doi: 10.1016/j.compag.2023.107622 – ident: 17091 doi: 10.1016/j.neucom.2023.01.087 – ident: 17077 doi: 10.1079/9780851996967.0059 – ident: 17075 doi: 10.1371/journal.pone.0135390 – ident: 17064 doi: 10.1007/978-981-10-3644-6_2 – ident: 17067 doi: 10.1016/j.compbiomed.2023.106726 – ident: 17066 doi: 10.1016/j.dt.2021.02.005 – ident: 17092 doi: 10.1039/D1FO01148K – ident: 17073 doi: 10.1016/j.jisa.2018.03.009 – ident: 17059 doi: 10.1016/j.eswa.2023.119614 – ident: 17083 doi: 10.1007/s00521-022-07793-2 – ident: 17078 doi: 10.17660/ActaHortic.2010.863.1 – ident: 17086 doi: 10.3389/fpls.2022.1066115 – ident: 17079 doi: 10.1016/j.scienta.2020.109360 – ident: 17093 doi: 10.1016/j.compag.2022.106805 – ident: 17096 – ident: 17070 doi: 10.1109/CVPR52688.2022.00714 – ident: 17085 doi: 10.1007/978-3-030-01234-2_1 – ident: 17060 doi: 10.1016/j.compbiomed.2023.106575 – ident: 17087 doi: 10.1016/j.neucom.2021.01.042 – ident: 17084 doi: 10.1016/j.compind.2023.103872 – ident: 17089 – ident: 17097 doi: 10.1016/j.compbiomed.2022.106496 |
SSID | ssj0001299793 ssib055683572 ssib044743255 |
Score | 2.2632847 |
Snippet | Lychee, a key economic crop in southern China, has numerous similar-looking varieties. Classifying these can aid farmers in understanding each variety's growth... Lychee, a key economic crop in southern Chi, has numerous similar-looking varieties. Classifying these can aid farmers in understanding each variety's growth... |
SourceID | doaj proquest crossref |
SourceType | Open Website Aggregation Database Index Database |
SubjectTerms | Attention mechanism Classification Cultivars Image classification lychee classification Receptive field residual network Transfer learning |
SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEA6yJz2IT1xf5CDeotu82jmuooioB1HwFpImlRWsslv9_c60XR948OKtDS0NM5P5ZtLMN4wd6NwiqOZGgNWVQIQYCfBgBRQyLwGMDJIKnK9v7MW9vnwwD99afdGZsI4euBMcJudaE6FMnjAXARVhFMCC0l75KGNRkvdFGPuWTKEl4Staya-KS6LZUqavEO13XyBvGXkzoAOJCLQdAadGiDx-8kSgKfURYr36AVgtr_8vt91i0fkKW-6DSD7uJr_KFlK9xpbGj9OeSCOts3SFji0lTgOTdz_lFYaT4pEaQqTIJ8_oRnhJkTMdFWq1w7tm0pxwLXK8n7T7DXh9m2Y3qRFKc8zN2-ItXnenxzfY3fnZ3emF6FsqiBLjtEZUyqbcZuWoCBGXolXB0K9Yb0KVeyhNlqj1hiklxAJS9D6ztjA26AqDcAhqkw3qlzptMZ5VpcLcL3iIUpMmZMxAh1wn1G-swpAdzsXmXjviDIcJB8nXoXwdydeRfIfshIT6-RDxXbcDaAWutwL3lxUM2e5cJa5fhDOHoRG6K1Cgtv_jGztskSbd7b_sskEzfUt7GJE0Yb81vg_HnNZg priority: 102 providerName: Directory of Open Access Journals |
Title | Lychee cultivar fine-grained image classification method based on improved ResNet-34 residual network |
URI | https://www.proquest.com/docview/3173229393 https://doaj.org/article/204473287e18493d90b96934a3ad2d8c |
Volume | 55 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
journalDatabaseRights | – providerCode: PRVAFT databaseName: Open Access Digital Library customDbUrl: eissn: 2239-6268 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0001299793 issn: 1974-7071 databaseCode: KQ8 dateStart: 20070101 isFulltext: true titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html providerName: Colorado Alliance of Research Libraries – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2239-6268 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0001299793 issn: 1974-7071 databaseCode: DOA dateStart: 20070101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVEBS databaseName: EBSCOhost Academic Search Ultimate customDbUrl: https://search.ebscohost.com/login.aspx?authtype=ip,shib&custid=s3936755&profile=ehost&defaultdb=asn eissn: 2239-6268 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0001299793 issn: 1974-7071 databaseCode: ABDBF dateStart: 20120701 isFulltext: true titleUrlDefault: https://search.ebscohost.com/direct.asp?db=asn providerName: EBSCOhost – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2239-6268 dateEnd: 99991231 omitProxy: true ssIdentifier: ssib044743255 issn: 1974-7071 databaseCode: M~E dateStart: 20120101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: http://www.proquest.com/pqcentral?accountid=15518 eissn: 2239-6268 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0001299793 issn: 1974-7071 databaseCode: BENPR dateStart: 20090601 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3db9NADD_B9gIPaONDFEZ1D4i3Y819JX6aWliZEFRoGtLeovtK1Um0ow38_diXKxNC2lOSy0mJbJ9_tu9sM_ZW1xZBtTYCrO4EIsREgAMroJF1ADDSS0pw_rqwF9_152tzXQJuu3Kscq8Ts6KOm0Ax8lPEOZQ9UKDObn8K6hpFu6ulhcZDdlhJlCTKFJ9_2suT1giP8i7vkoptKVPyREsMBupcl7cCOpaIcDuU4dQIlKc3jspoSv0eEV_9A1u5uv9_yjsj0vyIPSmmJJ8OvD9mD1b9U_Z4utyWchrpGUtfUL2lxGlg9dtteYdGpVhSW4gU-eoHKhMeyH6mA0OZR3xoKc0J3SLH51WOOuD9ZdotUi-U5uih5xQuvh7OkD9nV_Pzqw8XojRWEAGttV50yqbaVmHS-IgL0ipvaEPWGd_VDoKpEjXgMEFCbCBF5yprG2O97tAUB69esIP1Zp1eMl51QaEH6B1EqaOMjYwVaF_rhFyOnR-xd3uytbdD-YwW3Q6ib4v0bYm-LdF3xGZE1L-TqOp1Hthsl21ZRDgbWarQx0vol4KKMPFgQWmnHH07jNjJniVtWYq79k5wXt3_-jV7RL8zxFdO2EG__ZXeoMXR-3EWqzE7nM4-zuZ4nZ0vvl2Os__-B5ug0z4 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELZKOQAHxFPdUsAH4Ga68SuZA0LlsWzpdg9okXqz7NhZLRK7JZuC-FH8R2byoEJI3HpLHCuJxp_9zYw9M4w907lFUs2NAKsrgQwxFuDBCihkXgIYGSQFOJ_O7fSz_nhmznbYryEWho5VDmtiu1DHTUk-8kPkOcQeKFCvz78JqhpFu6tDCY0OFifp5w802bavjt_h-D6XcvJ-8XYq-qoCokRVpRGVsglt93JchIhotCoY2o30JlS5h9JkiapPmFJCLCBF7zNrC2ODrlAPhaDwtdfYda2UolT9xeTDAF-tkY3lZZgn5fZSpg9L7V0-kLdpgDOgU5DI7l3WT428fPjFU9ZOqV-igqH-Ysm2mMA_XNES4OQOu91rrvyog9pdtrNq7rFbR8u6z96R7rM0w9U0JU4Nq---5hXqsGJJVShS5KuvuHbxktR1Op_UQoJ3Faw5kWnkeL9qnRx4_Slt56kRSvM6bduIMb7ujqw_YIurkPhDtrverNMe41lVKjQ4g4codZSxkDEDHXKdEFSxCiP2YhCbO--ydTi0cki-DuXrSL6O5Dtib0iofzpRku22YVMvXT9nsTcOqUKTMqEZDCrCOIAFpb3y9O1yxA6GIXH9zN-6S5zu___xU3Zjujidudnx_OQRu0m_1rl2DthuU1-kx6jsNOFJCzHO3BVD-jc22Qq0 |
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=Lychee+cultivar+fine-grained+image+classification+method+based+on+improved+ResNet-34+residual+network&rft.jtitle=Journal+of+agricultural+engineering+%28Pisa%2C+Italy%29&rft.au=Xiao%2C+Yiming&rft.au=Wang%2C+Jianhua&rft.au=Xiong%2C+Hongyi&rft.au=Xiao%2C+Fangjun&rft.date=2024-01-01&rft.pub=PAGEPress+Publications&rft.issn=1974-7071&rft.eissn=2239-6268&rft.volume=55&rft.issue=3&rft_id=info:doi/10.4081%2Fjae.2024.1593 |
thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1974-7071&client=summon |
thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1974-7071&client=summon |
thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1974-7071&client=summon |