Performance of vision transformer and swin transformer models for lemon quality classification in fruit juice factories
Assessing the quality of agricultural products holds vital significance in enhancing production efficiency and market viability. The adoption of artificial intelligence (AI) has notably surged for this purpose, employing deep learning and machine learning techniques to process and classify agricultu...
Gespeichert in:
| Veröffentlicht in: | European food research & technology 2024-09, Vol.250 (9), p.2291-2302 |
|---|---|
| Hauptverfasser: | , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2302 |
|---|---|
| container_issue | 9 |
| container_start_page | 2291 |
| container_title | European food research & technology |
| container_volume | 250 |
| creator | Dümen, Sezer Kavalcı Yılmaz, Esra Adem, Kemal Avaroglu, Erdinç |
| description | Assessing the quality of agricultural products holds vital significance in enhancing production efficiency and market viability. The adoption of artificial intelligence (AI) has notably surged for this purpose, employing deep learning and machine learning techniques to process and classify agricultural product images, adhering to defined standards. This study focuses on the lemon dataset, encompassing ‘good’ and ‘bad’ quality classes, initiate by augmenting data through rescaling, random zoom, flip, and rotation methods. Subsequently, employing eight diverse deep learning approaches and two transformer methods for classification, the study culminated in the ViT method achieving an unprecedented 99.84% accuracy, 99.95% recall, and 99.66% precision, marking the highest accuracy documented. These findings strongly advocate for the efficacy of the ViT method in successfully classifying lemon quality, spotlighting its potential impact on agricultural quality assessment. |
| doi_str_mv | 10.1007/s00217-024-04537-5 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_3084092143</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3084092143</sourcerecordid><originalsourceid>FETCH-LOGICAL-c347t-22068fda1e7c0ad616fb8e20fac81aaee0d962535d73be8539900c823010e94d3</originalsourceid><addsrcrecordid>eNp9kUtLxTAQhYMoqFf_gKuAGzfVSdL0sRTxBYIudB1iOpFc2kYzreK_N9crii5cTWb4zpkwh7EDAccCoD4hACnqAmRZQKlVXegNtiNK1RRSNXrz-13X22yXaAmg20qUO-ztDpOPabCjQx49fw0U4sinZEdazTFxO3ac3sLv4RA77Innjvc4ZMXLbPswvXPXW6Lgg7PTyijLfJrDxJdzyBu8dVNMAWmPbXnbE-5_1QV7uDi_P7sqbm4vr89ObwqnynoqpISq8Z0VWDuwXSUq_9ighOzTCGsRoWsrqZXuavWIjVZtC-AaqUAAtmWnFuxo7fuc4suMNJkhkMO-tyPGmYwS-VpCy3yfBTv8gy7jnMb8O6OgKaFdQZmSa8qlSJTQm-cUBpvejQCzysKsszA5C_OZhdFZpNYiyvD4hOnH-h_VB7lQjlM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3084092143</pqid></control><display><type>article</type><title>Performance of vision transformer and swin transformer models for lemon quality classification in fruit juice factories</title><source>SpringerLink</source><creator>Dümen, Sezer ; Kavalcı Yılmaz, Esra ; Adem, Kemal ; Avaroglu, Erdinç</creator><creatorcontrib>Dümen, Sezer ; Kavalcı Yılmaz, Esra ; Adem, Kemal ; Avaroglu, Erdinç</creatorcontrib><description>Assessing the quality of agricultural products holds vital significance in enhancing production efficiency and market viability. The adoption of artificial intelligence (AI) has notably surged for this purpose, employing deep learning and machine learning techniques to process and classify agricultural product images, adhering to defined standards. This study focuses on the lemon dataset, encompassing ‘good’ and ‘bad’ quality classes, initiate by augmenting data through rescaling, random zoom, flip, and rotation methods. Subsequently, employing eight diverse deep learning approaches and two transformer methods for classification, the study culminated in the ViT method achieving an unprecedented 99.84% accuracy, 99.95% recall, and 99.66% precision, marking the highest accuracy documented. These findings strongly advocate for the efficacy of the ViT method in successfully classifying lemon quality, spotlighting its potential impact on agricultural quality assessment.</description><identifier>ISSN: 1438-2377</identifier><identifier>EISSN: 1438-2385</identifier><identifier>DOI: 10.1007/s00217-024-04537-5</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer Berlin Heidelberg</publisher><subject>Accuracy ; Agricultural production ; Agricultural products ; Agriculture ; Analytical Chemistry ; Artificial intelligence ; Biotechnology ; Chemistry ; Chemistry and Materials Science ; Classification ; Computer engineering ; data collection ; Datasets ; Deep learning ; Discriminant analysis ; Disease ; economic sustainability ; Efficiency ; Food Science ; Forestry ; Fruit juices ; Image enhancement ; Image quality ; Lemons ; Machine learning ; Original Paper ; Quality assessment ; Quality control ; Rescaling ; Success ; vision</subject><ispartof>European food research & technology, 2024-09, Vol.250 (9), p.2291-2302</ispartof><rights>The Author(s) 2024</rights><rights>The Author(s) 2024. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c347t-22068fda1e7c0ad616fb8e20fac81aaee0d962535d73be8539900c823010e94d3</cites><orcidid>0000-0002-3752-7354</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s00217-024-04537-5$$EPDF$$P50$$Gspringer$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s00217-024-04537-5$$EHTML$$P50$$Gspringer$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,27922,27923,41486,42555,51317</link.rule.ids></links><search><creatorcontrib>Dümen, Sezer</creatorcontrib><creatorcontrib>Kavalcı Yılmaz, Esra</creatorcontrib><creatorcontrib>Adem, Kemal</creatorcontrib><creatorcontrib>Avaroglu, Erdinç</creatorcontrib><title>Performance of vision transformer and swin transformer models for lemon quality classification in fruit juice factories</title><title>European food research & technology</title><addtitle>Eur Food Res Technol</addtitle><description>Assessing the quality of agricultural products holds vital significance in enhancing production efficiency and market viability. The adoption of artificial intelligence (AI) has notably surged for this purpose, employing deep learning and machine learning techniques to process and classify agricultural product images, adhering to defined standards. This study focuses on the lemon dataset, encompassing ‘good’ and ‘bad’ quality classes, initiate by augmenting data through rescaling, random zoom, flip, and rotation methods. Subsequently, employing eight diverse deep learning approaches and two transformer methods for classification, the study culminated in the ViT method achieving an unprecedented 99.84% accuracy, 99.95% recall, and 99.66% precision, marking the highest accuracy documented. These findings strongly advocate for the efficacy of the ViT method in successfully classifying lemon quality, spotlighting its potential impact on agricultural quality assessment.</description><subject>Accuracy</subject><subject>Agricultural production</subject><subject>Agricultural products</subject><subject>Agriculture</subject><subject>Analytical Chemistry</subject><subject>Artificial intelligence</subject><subject>Biotechnology</subject><subject>Chemistry</subject><subject>Chemistry and Materials Science</subject><subject>Classification</subject><subject>Computer engineering</subject><subject>data collection</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Discriminant analysis</subject><subject>Disease</subject><subject>economic sustainability</subject><subject>Efficiency</subject><subject>Food Science</subject><subject>Forestry</subject><subject>Fruit juices</subject><subject>Image enhancement</subject><subject>Image quality</subject><subject>Lemons</subject><subject>Machine learning</subject><subject>Original Paper</subject><subject>Quality assessment</subject><subject>Quality control</subject><subject>Rescaling</subject><subject>Success</subject><subject>vision</subject><issn>1438-2377</issn><issn>1438-2385</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>C6C</sourceid><recordid>eNp9kUtLxTAQhYMoqFf_gKuAGzfVSdL0sRTxBYIudB1iOpFc2kYzreK_N9crii5cTWb4zpkwh7EDAccCoD4hACnqAmRZQKlVXegNtiNK1RRSNXrz-13X22yXaAmg20qUO-ztDpOPabCjQx49fw0U4sinZEdazTFxO3ac3sLv4RA77Innjvc4ZMXLbPswvXPXW6Lgg7PTyijLfJrDxJdzyBu8dVNMAWmPbXnbE-5_1QV7uDi_P7sqbm4vr89ObwqnynoqpISq8Z0VWDuwXSUq_9ighOzTCGsRoWsrqZXuavWIjVZtC-AaqUAAtmWnFuxo7fuc4suMNJkhkMO-tyPGmYwS-VpCy3yfBTv8gy7jnMb8O6OgKaFdQZmSa8qlSJTQm-cUBpvejQCzysKsszA5C_OZhdFZpNYiyvD4hOnH-h_VB7lQjlM</recordid><startdate>20240901</startdate><enddate>20240901</enddate><creator>Dümen, Sezer</creator><creator>Kavalcı Yılmaz, Esra</creator><creator>Adem, Kemal</creator><creator>Avaroglu, Erdinç</creator><general>Springer Berlin Heidelberg</general><general>Springer Nature B.V</general><scope>C6C</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7QO</scope><scope>7QR</scope><scope>7T7</scope><scope>8FD</scope><scope>C1K</scope><scope>FR3</scope><scope>P64</scope><scope>7S9</scope><scope>L.6</scope><orcidid>https://orcid.org/0000-0002-3752-7354</orcidid></search><sort><creationdate>20240901</creationdate><title>Performance of vision transformer and swin transformer models for lemon quality classification in fruit juice factories</title><author>Dümen, Sezer ; Kavalcı Yılmaz, Esra ; Adem, Kemal ; Avaroglu, Erdinç</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c347t-22068fda1e7c0ad616fb8e20fac81aaee0d962535d73be8539900c823010e94d3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Accuracy</topic><topic>Agricultural production</topic><topic>Agricultural products</topic><topic>Agriculture</topic><topic>Analytical Chemistry</topic><topic>Artificial intelligence</topic><topic>Biotechnology</topic><topic>Chemistry</topic><topic>Chemistry and Materials Science</topic><topic>Classification</topic><topic>Computer engineering</topic><topic>data collection</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Discriminant analysis</topic><topic>Disease</topic><topic>economic sustainability</topic><topic>Efficiency</topic><topic>Food Science</topic><topic>Forestry</topic><topic>Fruit juices</topic><topic>Image enhancement</topic><topic>Image quality</topic><topic>Lemons</topic><topic>Machine learning</topic><topic>Original Paper</topic><topic>Quality assessment</topic><topic>Quality control</topic><topic>Rescaling</topic><topic>Success</topic><topic>vision</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Dümen, Sezer</creatorcontrib><creatorcontrib>Kavalcı Yılmaz, Esra</creatorcontrib><creatorcontrib>Adem, Kemal</creatorcontrib><creatorcontrib>Avaroglu, Erdinç</creatorcontrib><collection>Springer Open Access</collection><collection>CrossRef</collection><collection>Biotechnology Research Abstracts</collection><collection>Chemoreception Abstracts</collection><collection>Industrial and Applied Microbiology Abstracts (Microbiology A)</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>Engineering Research Database</collection><collection>Biotechnology and BioEngineering Abstracts</collection><collection>AGRICOLA</collection><collection>AGRICOLA - Academic</collection><jtitle>European food research & technology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Dümen, Sezer</au><au>Kavalcı Yılmaz, Esra</au><au>Adem, Kemal</au><au>Avaroglu, Erdinç</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Performance of vision transformer and swin transformer models for lemon quality classification in fruit juice factories</atitle><jtitle>European food research & technology</jtitle><stitle>Eur Food Res Technol</stitle><date>2024-09-01</date><risdate>2024</risdate><volume>250</volume><issue>9</issue><spage>2291</spage><epage>2302</epage><pages>2291-2302</pages><issn>1438-2377</issn><eissn>1438-2385</eissn><abstract>Assessing the quality of agricultural products holds vital significance in enhancing production efficiency and market viability. The adoption of artificial intelligence (AI) has notably surged for this purpose, employing deep learning and machine learning techniques to process and classify agricultural product images, adhering to defined standards. This study focuses on the lemon dataset, encompassing ‘good’ and ‘bad’ quality classes, initiate by augmenting data through rescaling, random zoom, flip, and rotation methods. Subsequently, employing eight diverse deep learning approaches and two transformer methods for classification, the study culminated in the ViT method achieving an unprecedented 99.84% accuracy, 99.95% recall, and 99.66% precision, marking the highest accuracy documented. These findings strongly advocate for the efficacy of the ViT method in successfully classifying lemon quality, spotlighting its potential impact on agricultural quality assessment.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer Berlin Heidelberg</pub><doi>10.1007/s00217-024-04537-5</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-3752-7354</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1438-2377 |
| ispartof | European food research & technology, 2024-09, Vol.250 (9), p.2291-2302 |
| issn | 1438-2377 1438-2385 |
| language | eng |
| recordid | cdi_proquest_journals_3084092143 |
| source | SpringerLink |
| subjects | Accuracy Agricultural production Agricultural products Agriculture Analytical Chemistry Artificial intelligence Biotechnology Chemistry Chemistry and Materials Science Classification Computer engineering data collection Datasets Deep learning Discriminant analysis Disease economic sustainability Efficiency Food Science Forestry Fruit juices Image enhancement Image quality Lemons Machine learning Original Paper Quality assessment Quality control Rescaling Success vision |
| title | Performance of vision transformer and swin transformer models for lemon quality classification in fruit juice factories |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T14%3A42%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Performance%20of%20vision%20transformer%20and%20swin%20transformer%20models%20for%20lemon%20quality%20classification%20in%20fruit%20juice%20factories&rft.jtitle=European%20food%20research%20&%20technology&rft.au=D%C3%BCmen,%20Sezer&rft.date=2024-09-01&rft.volume=250&rft.issue=9&rft.spage=2291&rft.epage=2302&rft.pages=2291-2302&rft.issn=1438-2377&rft.eissn=1438-2385&rft_id=info:doi/10.1007/s00217-024-04537-5&rft_dat=%3Cproquest_cross%3E3084092143%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=3084092143&rft_id=info:pmid/&rfr_iscdi=true |