Quantum Image Representations based Quantum Neural Networks for Binary Classification

Quantum Image Representations based Quantum Neural Networks for Binary Classification | 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 Quantum Image Representations based Quantum Neural Networks for Binary Classification Abhishek Tiwari, Shivanshu Siyanwal, Saiyam Sakhuja, Sachin Kumar, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7621070/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract We propose a comparative analysis of quantum image classification utilising a circularly-entangled quantum neural network (QNN) in conjunction with four quantum image representation (QIR) strategies: Novel Amplitude Square Sum (NASS), Quantum Block Image Representation (QBIR), Fourier-based Threshold Quantum Representation (FTQR), and Flexible Representation for Quantum Color Image (FRQCI). A methodical assessment of accuracy, loss convergence, and quantum resource requirements was made possible by the encoding of binary MNIST digits (0 and 1) at image sizes of \((2\times2)\) , \((4\times4)\) , and \((8\times8)\) . Our findings demonstrate that, whereas QBIR-QNN offers competitive results with shallow circuits at the expense of greater qubit counts, NASS-QNN continuously converges to high training accuracy with stable parameters, achieving the most reliable and accurate performance. On the other hand, the instability and large resource overheads of FTQR-QNN and FRQCI-QNN restrict their applicability in the NISQ regime. The most promising approaches are highlighted by these results: NASS and QBIR, which provide workable trade-offs between hardware implementability, accuracy, and convergence stability. Quantum Image Representations Normal Arbitrary Superposition State Quantum Block Image Representation Fourier Transform Qubit Representation Flexible Representation of Quantum Color Images Quantum Neural Network Modified National Institute of Standards and Technology Noisy Intermediate-Scale Quantum Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-7621070","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":532022119,"identity":"52951727-4e57-4253-a1db-d4a0824df7dc","order_by":0,"name":"Abhishek Tiwari","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAv0lEQVRIiWNgGAWjYDACCR6GA4wNDAb8DAwGIC4JWiQbSNHCANJicACshQjAP7v34MGfO2yMjY8f3vjhB4NFHmFL7pxLOMx7Js3M7ExasWQPg0QxYWtu5BgcZmw7bGN2g8dAGmhEYgMhHfJALQd/tv23MZ7BY/ybKC0GQC0HeNsOmBlI8JgRZ4vhnTMGh3nbko0lzqSVWfYYEKFF7naP8cefbXaG/e2HN9/4UVFHWAu6O0lUPwpGwSgYBaMAOwAAb6E94eoU4LkAAAAASUVORK5CYII=","orcid":"","institution":"Centre for Development of Advanced Computing","correspondingAuthor":true,"prefix":"","firstName":"Abhishek","middleName":"","lastName":"Tiwari","suffix":""},{"id":532022120,"identity":"4a2740f7-a300-4753-be71-d76ca2ba28b0","order_by":1,"name":"Shivanshu Siyanwal","email":"","orcid":"","institution":"Centre for Development of Advanced Computing","correspondingAuthor":false,"prefix":"","firstName":"Shivanshu","middleName":"","lastName":"Siyanwal","suffix":""},{"id":532022121,"identity":"7b4b3dfe-7776-49f8-9549-067311b618ba","order_by":2,"name":"Saiyam Sakhuja","email":"","orcid":"","institution":"Centre for Development of Advanced Computing","correspondingAuthor":false,"prefix":"","firstName":"Saiyam","middleName":"","lastName":"Sakhuja","suffix":""},{"id":532022122,"identity":"2de59635-8f5c-4c16-bf64-5c37baf2be28","order_by":3,"name":"Sachin Kumar","email":"","orcid":"","institution":"University of Delhi","correspondingAuthor":false,"prefix":"","firstName":"Sachin","middleName":"","lastName":"Kumar","suffix":""},{"id":532022123,"identity":"3db761d8-ce16-4ff7-b1ef-d7a85439b640","order_by":4,"name":"Pankaj Tyagi","email":"","orcid":"","institution":"University of Delhi","correspondingAuthor":false,"prefix":"","firstName":"Pankaj","middleName":"","lastName":"Tyagi","suffix":""}],"badges":[],"createdAt":"2025-09-15 13:23:38","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7621070/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7621070/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94747091,"identity":"17a75df0-b4e1-4010-9dfc-ad0014699aed","added_by":"auto","created_at":"2025-10-30 09:47:32","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6442,"visible":true,"origin":"","legend":"","description":"","filename":"3ba8623a3fef4314870daca69d35d19a.json","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/76a6d2afc95d6d97831379ef.json"},{"id":94747093,"identity":"dfc543d3-3220-4310-aa03-b39cee3ef59c","added_by":"auto","created_at":"2025-10-30 09:47:32","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":224033,"visible":true,"origin":"","legend":"","description":"","filename":"3ba8623a3fef4314870daca69d35d19a1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/c782da0493db5750e65c936f.xml"},{"id":94823169,"identity":"70c08d6b-789e-4967-985d-31d4e1c33f58","added_by":"auto","created_at":"2025-10-31 06:46:34","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1909960,"visible":true,"origin":"","legend":"","description":"","filename":"CDACNoidaQIIQIPSN2025main5.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/d1883049ea8f4825a9e153f0.pdf"},{"id":94822977,"identity":"a8313df8-0bb7-4e6b-a50b-0f5f8e3f3aaf","added_by":"auto","created_at":"2025-10-31 06:45:40","extension":"pdf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1909963,"visible":true,"origin":"","legend":"","description":"","filename":"CDACNoidaQIIQIPSN2025main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/752d32c6d9a1abb16ff8e940.pdf"},{"id":94747092,"identity":"586224b2-d2d6-4ba2-a7b2-0fde68b5667a","added_by":"auto","created_at":"2025-10-30 09:47:32","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":71881,"visible":true,"origin":"","legend":"","description":"","filename":"CDACNoidaQIIQPISN2025CoverLetter.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/fd9b86ce53a8eff8050824a5.pdf"},{"id":94823804,"identity":"0cee5586-b378-4b38-9fbb-ef54da5c0943","added_by":"auto","created_at":"2025-10-31 06:48:00","extension":"eps","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":300850,"visible":true,"origin":"","legend":"","description":"","filename":"n123paramevolution.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/c485f29dff588aa46db68708.eps"},{"id":94823771,"identity":"2fdea87a-4b6f-45ea-a2b4-5bace0ce45c5","added_by":"auto","created_at":"2025-10-31 06:47:57","extension":"eps","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27893,"visible":true,"origin":"","legend":"","description":"","filename":"n1FRQCIcircuitfirst20.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/7d6876322b187b83e37d9470.eps"},{"id":94824078,"identity":"23d5f07e-d821-4d9d-867e-cb4f0a4c6257","added_by":"auto","created_at":"2025-10-31 06:48:26","extension":"eps","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25900,"visible":true,"origin":"","legend":"","description":"","filename":"n1FTQRcircuitfirst20.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/e64c404dadb8590e8b6d5c61.eps"},{"id":94747097,"identity":"026d26d2-9b91-4304-8c87-bf059ca5a315","added_by":"auto","created_at":"2025-10-30 09:47:32","extension":"eps","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25051,"visible":true,"origin":"","legend":"","description":"","filename":"n1NASScircuitfirst20.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/3279c5f3289befa8a018c214.eps"},{"id":94823778,"identity":"8bc40dd1-85ed-4a2f-ac8a-76567dad2079","added_by":"auto","created_at":"2025-10-31 06:47:58","extension":"eps","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":44003,"visible":true,"origin":"","legend":"","description":"","filename":"n1accuracyplotallstrategies.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/1b1ecaa13136a96b1dcd3bc7.eps"},{"id":94747101,"identity":"186a40ca-b0f4-4ba5-b7bb-084c8f9ddca1","added_by":"auto","created_at":"2025-10-30 09:47:32","extension":"eps","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":44155,"visible":true,"origin":"","legend":"","description":"","filename":"n1lossplotallstrategies.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/63f4aaab22e442567159b506.eps"},{"id":94747102,"identity":"8c29a241-9a54-4f5a-b13e-f7f4503c1d71","added_by":"auto","created_at":"2025-10-30 09:47:32","extension":"eps","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35384,"visible":true,"origin":"","legend":"","description":"","filename":"n1trainparamsubplotfrqci.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/2341a90fc58faaf94157da5a.eps"},{"id":94823859,"identity":"9f1419f9-4438-48c5-8617-aefceb28e177","added_by":"auto","created_at":"2025-10-31 06:48:09","extension":"eps","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30204,"visible":true,"origin":"","legend":"","description":"","filename":"n1trainparamsubplotftqr.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/ac3a2226dad894f40c75be19.eps"},{"id":94823733,"identity":"3d01333e-34ce-4f93-8b06-9d278151a95b","added_by":"auto","created_at":"2025-10-31 06:47:55","extension":"eps","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28084,"visible":true,"origin":"","legend":"","description":"","filename":"n1trainparamsubplotnass.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/bc206ac14d215d2df60fcd8b.eps"},{"id":94747099,"identity":"48d6ca6c-6d37-42e3-977e-4f2831b904a0","added_by":"auto","created_at":"2025-10-30 09:47:32","extension":"eps","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":44282,"visible":true,"origin":"","legend":"","description":"","filename":"n1trainparamsubplotqbir.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/8c4029b20f9ecf12916e98b5.eps"},{"id":94747119,"identity":"3411038e-13b3-4901-9a8b-1442845c8df9","added_by":"auto","created_at":"2025-10-30 09:47:33","extension":"eps","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":44165,"visible":true,"origin":"","legend":"","description":"","filename":"n2accuracyplotallstrategies.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/55cf96abaf4a9f23e3c10aa5.eps"},{"id":94823171,"identity":"9394b301-9a9c-46c6-94a3-9fe7591d4640","added_by":"auto","created_at":"2025-10-31 06:46:34","extension":"eps","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":45608,"visible":true,"origin":"","legend":"","description":"","filename":"n2lossplotallstrategies.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/bd0f45ad78eb64bf559e453b.eps"},{"id":94822893,"identity":"fe823724-ec2f-4fcf-8dff-9e5d02747c6d","added_by":"auto","created_at":"2025-10-31 06:44:59","extension":"eps","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36595,"visible":true,"origin":"","legend":"","description":"","filename":"n2trainparamsubplotfrqci.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/5f8a6cf70faac283ec1086c7.eps"},{"id":94822979,"identity":"b546b577-7620-4270-b678-b5894c665a5a","added_by":"auto","created_at":"2025-10-31 06:45:40","extension":"eps","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35893,"visible":true,"origin":"","legend":"","description":"","filename":"n2trainparamsubplotftqr.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/6f1536180ed7759fc6b8647e.eps"},{"id":94823863,"identity":"ce29a614-3bcc-49cc-9826-4e988546d827","added_by":"auto","created_at":"2025-10-31 06:48:10","extension":"eps","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33858,"visible":true,"origin":"","legend":"","description":"","filename":"n2trainparamsubplotnass.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/47a9df2383a01b7531a4ec02.eps"},{"id":94747105,"identity":"7fa5fe35-9bbb-48c8-b0ca-2dae71dc1c14","added_by":"auto","created_at":"2025-10-30 09:47:32","extension":"eps","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49854,"visible":true,"origin":"","legend":"","description":"","filename":"n2trainparamsubplotqbir.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/262d9976438fe2c4fb5ae720.eps"},{"id":94823258,"identity":"619c8022-786b-4e61-afdf-038fa0ee0488","added_by":"auto","created_at":"2025-10-31 06:46:53","extension":"eps","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":45917,"visible":true,"origin":"","legend":"","description":"","filename":"n3accuracyplotallstrategies.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/16da0f899e2684cfa85808b0.eps"},{"id":94823331,"identity":"a546e73c-bd17-4b32-899c-9f2581021583","added_by":"auto","created_at":"2025-10-31 06:47:05","extension":"eps","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":44074,"visible":true,"origin":"","legend":"","description":"","filename":"n3lossplotallstrategies.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/a8d3e76d02ebca70a16eb18b.eps"},{"id":94823048,"identity":"0976e107-d944-4c37-83f2-915b43901692","added_by":"auto","created_at":"2025-10-31 06:45:57","extension":"eps","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"n3trainparamsubplotfrqci.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/45bae61b4129ca449b644a8d.eps"},{"id":94747116,"identity":"da926022-666c-4e33-bb7f-dc10f5754e73","added_by":"auto","created_at":"2025-10-30 09:47:32","extension":"eps","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39337,"visible":true,"origin":"","legend":"","description":"","filename":"n3trainparamsubplotftqr.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/989fcecb8c082bcb64c383fc.eps"},{"id":94747111,"identity":"bdcbf328-9ced-46a0-9ad0-3d2a6a70ba5b","added_by":"auto","created_at":"2025-10-30 09:47:32","extension":"eps","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36863,"visible":true,"origin":"","legend":"","description":"","filename":"n3trainparamsubplotnass.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/cae2920fbf5c2f9a1ab7b3d3.eps"},{"id":94747107,"identity":"af9bbb34-286a-49ed-8243-433f0514c215","added_by":"auto","created_at":"2025-10-30 09:47:32","extension":"eps","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":53320,"visible":true,"origin":"","legend":"","description":"","filename":"n3trainparamsubplotqbir.eps","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/ea29f965816747ee0bc31bb6.eps"},{"id":94823008,"identity":"6506a8ca-39ee-4692-80e2-d50d3747dbd2","added_by":"auto","created_at":"2025-10-31 06:45:47","extension":"cls","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/54e0ce36aadaeb7cab6f3717.cls"},{"id":94823562,"identity":"988eee26-dfc8-4546-9ea6-212e11032d95","added_by":"auto","created_at":"2025-10-31 06:47:37","extension":"bst","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/c4a4c0fb80b14006a9b34910.bst"},{"id":94747120,"identity":"cd97ff27-b243-490d-af4a-5e458e1a52ed","added_by":"auto","created_at":"2025-10-30 09:47:33","extension":"xml","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":236080,"visible":true,"origin":"","legend":"","description":"","filename":"3ba8623a3fef4314870daca69d35d19a1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/0d86d38c4505621ec69639e4.xml"},{"id":94747121,"identity":"5820f326-ca4a-469e-a166-eb32db630268","added_by":"auto","created_at":"2025-10-30 09:47:33","extension":"html","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":266599,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1/8b86a656e01533ee117d13d3.html"},{"id":95528311,"identity":"838d9ab2-b015-4839-9d0c-9b5a164b8cc5","added_by":"auto","created_at":"2025-11-10 10:15:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1767538,"visible":true,"origin":"","legend":"","description":"","filename":"CDACNoidaQIIQIPSN2025main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7621070/v1_covered_adec7e06-2a2a-4f0b-9975-89239c57d47c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Quantum Image Representations based Quantum Neural Networks for Binary Classification","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Quantum Image Representations, Normal Arbitrary Superposition State, Quantum Block Image Representation, Fourier Transform Qubit Representation, Flexible Representation of Quantum Color Images, Quantum Neural Network, Modified National Institute of Standards and Technology, Noisy Intermediate-Scale Quantum","lastPublishedDoi":"10.21203/rs.3.rs-7621070/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7621070/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWe propose a comparative analysis of quantum image classification utilising a circularly-entangled quantum neural network (QNN) in conjunction with four quantum image representation (QIR) strategies: Novel Amplitude Square Sum (NASS), Quantum Block Image Representation (QBIR), Fourier-based Threshold Quantum Representation (FTQR), and Flexible Representation for Quantum Color Image (FRQCI). A methodical assessment of accuracy, loss convergence, and quantum resource requirements was made possible by the encoding of binary MNIST digits (0 and 1) at image sizes of \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\((2\\times2)\\)\u003c/span\u003e\u003c/span\u003e, \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\((4\\times4)\\)\u003c/span\u003e\u003c/span\u003e, and \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\((8\\times8)\\)\u003c/span\u003e\u003c/span\u003e. Our findings demonstrate that, whereas QBIR-QNN offers competitive results with shallow circuits at the expense of greater qubit counts, NASS-QNN continuously converges to high training accuracy with stable parameters, achieving the most reliable and accurate performance. On the other hand, the instability and large resource overheads of FTQR-QNN and FRQCI-QNN restrict their applicability in the NISQ regime. The most promising approaches are highlighted by these results: NASS and QBIR, which provide workable trade-offs between hardware implementability, accuracy, and convergence stability. \u003c/p\u003e","manuscriptTitle":"Quantum Image Representations based Quantum Neural Networks for Binary Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-30 09:47:27","doi":"10.21203/rs.3.rs-7621070/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"3bc9b63c-0057-4b2b-b9c3-3141ca5a1e84","owner":[],"postedDate":"October 30th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-11-10T04:08:46+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-30 09:47:27","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7621070","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7621070","identity":"rs-7621070","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}