Interpretable Color–Texture–Shape Feature Fusion for RGB-Based Citrus Canker and Melanose Classification on Orange Fruit

Interpretable Color–Texture–Shape Feature Fusion for RGB-Based Citrus Canker and Melanose Classification on Orange Fruit | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Interpretable Color–Texture–Shape Feature Fusion for RGB-Based Citrus Canker and Melanose Classification on Orange Fruit Hoa-Cuc. Nguyen, Ngoc-Duong. Nguyen, Viet-Hung. Pham, Bich-Ngoc. Mach, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9594358/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract Citrus canker and melanose substantially reduce the visual quality and commercial value of orange fruit, yet routine diagnosis remains largely dependent on subjective visual inspection. This study presents an interpretable color–texture–shape feature fusion framework for RGB-based classification of healthy, canker-infected, and melanose-affected orange fruit. Each image was represented by a compact descriptor integrating HSV color histograms, Local Binary Pattern micro-texture features, and Histogram of Oriented Gradients edge–shape information, followed by normalized feature concatenation and one-vs-rest Logistic Regression classification. On a balanced held-out test set, the proposed pipeline achieved 93.93% overall accuracy and a macro-F1 score of approximately 0.94, with class-wise F1-scores of 0.927 for citrus canker, 0.933 for healthy fruit, and 0.958 for melanose. Error analysis showed that residual misclassifications were concentrated mainly along the canker–healthy boundary. These findings demonstrate that well-designed handcrafted descriptors can provide accurate, transparent, and diagnostically meaningful citrus fruit disease recognition. Citrus canker Melanose Orange fruit disease RGB image classification HSV color histogram Local Binary Pattern Histogram of Oriented Gradients Logistic Regression Interpretable machine learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 04 May, 2026 Editor assigned by journal 02 May, 2026 Submission checks completed at journal 02 May, 2026 First submitted to journal 02 May, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9594358","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":633896814,"identity":"bcea3a5e-38eb-4b40-9128-07d42a4158ba","order_by":0,"name":"Hoa-Cuc. Nguyen","email":"","orcid":"","institution":"Thu Dau Mot University","correspondingAuthor":false,"prefix":"","firstName":"Hoa-Cuc.","middleName":"","lastName":"Nguyen","suffix":""},{"id":633896815,"identity":"79ca0e6a-f5ac-4fda-ba77-a21d5612b43e","order_by":1,"name":"Ngoc-Duong. Nguyen","email":"","orcid":"","institution":"Thu Dau Mot University","correspondingAuthor":false,"prefix":"","firstName":"Ngoc-Duong.","middleName":"","lastName":"Nguyen","suffix":""},{"id":633896816,"identity":"85b24086-1cd6-4144-a146-68b34348a115","order_by":2,"name":"Viet-Hung. Pham","email":"","orcid":"","institution":"Thu Dau Mot University","correspondingAuthor":false,"prefix":"","firstName":"Viet-Hung.","middleName":"","lastName":"Pham","suffix":""},{"id":633896817,"identity":"83d13591-1d41-4fdb-b775-e7c4fb04e52b","order_by":3,"name":"Bich-Ngoc. Mach","email":"","orcid":"","institution":"Thu Dau Mot University","correspondingAuthor":false,"prefix":"","firstName":"Bich-Ngoc.","middleName":"","lastName":"Mach","suffix":""},{"id":633896818,"identity":"4f247a1b-ce53-4615-9e1a-8b930cbf1827","order_by":4,"name":"Trinh Thi Nhu Quynh","email":"","orcid":"","institution":"Thu Dau Mot University","correspondingAuthor":false,"prefix":"","firstName":"Trinh","middleName":"Thi Nhu","lastName":"Quynh","suffix":""},{"id":633896819,"identity":"39f92e48-adc8-4c1b-b894-0bc60a1f069b","order_by":5,"name":"Duong Thi Kim Chi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYDACCcYGCYYDNgwMB0A8NmK1HDiQJkGKFiA6cOAwCVr4Zzc33v5w5nwd37UzBgwfyg4zGNxuIGDJnYPNFgdu3JaQvJ1jwDjjHFDLnQP4tRhIJLZJHPhwW8IAqIWZt+0wg+SMBKK0nINo+Uu8lhsHIFoYgVr4JQhokbiR2Gxx5kyy5MzbaQUHe86l8xDUwj8j/eGNimN2/Hy3kzc++FFmLcdGSAsKOADEPCSoHwWjYBSMglGACwAA75hKq/eDP3UAAAAASUVORK5CYII=","orcid":"","institution":"Thu Dau Mot University","correspondingAuthor":true,"prefix":"","firstName":"Duong","middleName":"Thi Kim","lastName":"Chi","suffix":""}],"badges":[],"createdAt":"2026-05-02 14:08:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9594358/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9594358/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108978093,"identity":"53abf762-9f7f-4043-a2a5-83cdf32fe0e1","added_by":"auto","created_at":"2026-05-11 11:34:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":413954,"visible":true,"origin":"","legend":"","description":"","filename":"InterpretableColor.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9594358/v1_covered_cfadcde5-06dc-44d7-87ae-a9a9868ee9ed.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Interpretable Color–Texture–Shape Feature Fusion for RGB-Based Citrus Canker and Melanose Classification on Orange Fruit","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":false,"email":"","identity":"applied-fruit-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Applied Fruit Science","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"VoR Journals","inReviewEnabled":false,"inReviewRevisionsEnabled":false},"keywords":"Citrus canker, Melanose, Orange fruit disease, RGB image classification, HSV color histogram, Local Binary Pattern, Histogram of Oriented Gradients, Logistic Regression, Interpretable machine learning","lastPublishedDoi":"10.21203/rs.3.rs-9594358/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9594358/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCitrus canker and melanose substantially reduce the visual quality and commercial value of orange fruit, yet routine diagnosis remains largely dependent on subjective visual inspection. This study presents an interpretable color\u0026ndash;texture\u0026ndash;shape feature fusion framework for RGB-based classification of healthy, canker-infected, and melanose-affected orange fruit. Each image was represented by a compact descriptor integrating HSV color histograms, Local Binary Pattern micro-texture features, and Histogram of Oriented Gradients edge\u0026ndash;shape information, followed by normalized feature concatenation and one-vs-rest Logistic Regression classification. On a balanced held-out test set, the proposed pipeline achieved 93.93% overall accuracy and a macro-F1 score of approximately 0.94, with class-wise F1-scores of 0.927 for citrus canker, 0.933 for healthy fruit, and 0.958 for melanose. Error analysis showed that residual misclassifications were concentrated mainly along the canker\u0026ndash;healthy boundary. These findings demonstrate that well-designed handcrafted descriptors can provide accurate, transparent, and diagnostically meaningful citrus fruit disease recognition.\u003c/p\u003e","manuscriptTitle":"Interpretable Color–Texture–Shape Feature Fusion for RGB-Based Citrus Canker and Melanose Classification on Orange Fruit","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-11 05:02:10","doi":"10.21203/rs.3.rs-9594358/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-05-04T06:39:09+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-02T15:49:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-05-02T15:49:48+00:00","index":"","fulltext":""},{"type":"submitted","content":"Applied Fruit Science","date":"2026-05-02T13:54:43+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":false,"email":"","identity":"applied-fruit-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Applied Fruit Science","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"VoR Journals","inReviewEnabled":false,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"49f49ec0-4eb3-42d6-a6bf-d0dabd12d606","owner":[],"postedDate":"May 11th, 2026","published":true,"recentEditorialEvents":[{"type":"reviewersInvited","content":"3","date":"2026-05-04T06:39:09+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-02T15:49:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-05-02T15:49:48+00:00","index":"","fulltext":""},{"type":"submitted","content":"Applied Fruit Science","date":"2026-05-02T13:54:43+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-11T05:02:11+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-11 05:02:10","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9594358","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9594358","identity":"rs-9594358","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}