Object extraction in a quantum inspired soft computing environment
| dc.contributor.guide | Bhattacharyya, Siddhartha | |
| dc.coverage.spatial | Soft computing | |
| dc.creator.researcher | Pal, Pankaj | |
| dc.date.accessioned | 2023-01-18T12:36:47Z | |
| dc.date.available | 2023-01-18T12:36:47Z | |
| dc.date.awarded | 2022 | |
| dc.date.completed | 2021 | |
| dc.date.registered | 2016 | |
| dc.description.abstract | Differentkindsofnoiseremovalintelligenttechniquesarebeingusedtoex- newlinetract objectsbymeansofremovalofnoiseartifacts.Amongtheintelligenttools newlinein vogue,theMulti-LayerSelfOrganizingNeuralNetworkarchitecture(ML- newlineSONN) architectureisefficientinextractingobjectsfromblurredandnoisybi- newlinenary images.Grayscaleimagesaresegmentedusingthenetworkbyresorting newlineto amultilevelsigmoidalactivationfunctionsoastoelicitnetworkresponses newlineto allpossiblegrayscales.AparallelMulti-LayerSelfOrganizingNeuralNet- newlinework architecture(PSONN)comprisingthreeparallelMulti-LayerSelfOrganiz- newlineing NeuralNetworkarchitectureswith/withoutmultilevelsigmoidalactivation newlinefunctions canbeusedtoextractpureandtruecolornoisyimages. newlineIn thisthesis,aquantumversionoftheMLSONNarchitectureisproposedtoex- newlinetract andsegmentnoisyimages.TheproposedQMLSONNnetworkarchitecture newlinecomprises threedifferentlayersviz.inputlayer,hiddenlayerandoutputlayer newlineenvisaged by qubit neurons,whereeach qubit neuronineachlayercorresponds newlineto eachpixeloftheinputimage.Theinterconnectionweightsbetweenthediffer- newlineent layersarerepresentedasquantumrotationgates.The qubit neuronhasthe newlineability toextracttheobjectsbyresortingtotheprincipleofquantumsuperposi- newlinetion. newlineThe qubit neuronsofthethreenetworklayersprocesstheimageinformationus- newlineing quantumrotationgatesasinterconnectionweightsguidedbyaquantum newlinebackpropagationalgorithm.Attheoutputlayer,aquantummeasurementis newlineused todestroythequantumstatestoyieldnetworkoutputswhiletheinter- newlineconnection weightsareadjustedusingaquantumbackpropagationalgorithm. newlineA parallelversionoftheproposedarchitecturecomprisingthreeindependent newlineQMLSONN architectures(referredtoasQPSONN)witheacharchitectureen- newlinetrustedforprocessingthethreeindividualprimarycolorcomponents(R,G,B), newlineis alsoproposedtoextractcolorobjectsfrompurecolornoisyimages. newlineA functionalmodificationoftheproposedQMLSONNarchitectureisachieved newlineby incorporatingaMultilevelSigmoidal(MUSIG)activationfunctionsothatthe newlinenetwork isabletosegmentmultilevelgrayscaleimages.Onsimilarlines,the newlineQPSONN architectureisalsomodifiedbyincorporatingmultilevelcharacte | |
| dc.description.note | ||
| dc.format.accompanyingmaterial | None | |
| dc.format.dimensions | 22cmx30cm | |
| dc.format.extent | xxiv,184p | |
| dc.identifier.uri | http://hdl.handle.net/10603/449431 | |
| dc.language | English | |
| dc.publisher.institution | Department of Computer Science and Engineering | |
| dc.publisher.place | Kolkata | |
| dc.publisher.university | Maulana Abul Kalam Azad University of Technology | |
| dc.relation | ||
| dc.rights | university | |
| dc.source.university | University | |
| dc.subject.keyword | Computer Science | |
| dc.subject.keyword | Computer Science Software Engineering | |
| dc.subject.keyword | Engineering and Technology | |
| dc.subject.keyword | Intelligent control systems | |
| dc.title | Object extraction in a quantum inspired soft computing environment | |
| dc.title.alternative | ||
| dc.type.degree | Ph.D. |
Files
Original bundle
1 - 5 of 12
Loading...
- Name:
- 01_title page.pdf
- Size:
- 27.23 KB
- Format:
- Adobe Portable Document Format
- Description:
- Attached File
Loading...
- Name:
- 02_prelim_pages.pdf
- Size:
- 118.82 KB
- Format:
- Adobe Portable Document Format
License bundle
1 - 1 of 1