Object extraction in a quantum inspired soft computing environment

dc.contributor.guideBhattacharyya, Siddhartha
dc.coverage.spatialSoft computing
dc.creator.researcherPal, Pankaj
dc.date.accessioned2023-01-18T12:36:47Z
dc.date.available2023-01-18T12:36:47Z
dc.date.awarded2022
dc.date.completed2021
dc.date.registered2016
dc.description.abstractDifferentkindsofnoiseremovalintelligenttechniquesarebeingusedtoex- 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.accompanyingmaterialNone
dc.format.dimensions22cmx30cm
dc.format.extentxxiv,184p
dc.identifier.urihttp://hdl.handle.net/10603/449431
dc.languageEnglish
dc.publisher.institutionDepartment of Computer Science and Engineering
dc.publisher.placeKolkata
dc.publisher.universityMaulana Abul Kalam Azad University of Technology
dc.relation
dc.rightsuniversity
dc.source.universityUniversity
dc.subject.keywordComputer Science
dc.subject.keywordComputer Science Software Engineering
dc.subject.keywordEngineering and Technology
dc.subject.keywordIntelligent control systems
dc.titleObject extraction in a quantum inspired soft computing environment
dc.title.alternative
dc.type.degreePh.D.

Files

Original bundle

Now showing 1 - 5 of 12
Loading...
Thumbnail Image
Name:
01_title page.pdf
Size:
27.23 KB
Format:
Adobe Portable Document Format
Description:
Attached File
Loading...
Thumbnail Image
Name:
02_prelim_pages.pdf
Size:
118.82 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
03_content.pdf
Size:
31.63 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
04_abstract.pdf
Size:
30.56 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
05_chapter 1.pdf
Size:
479.32 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.79 KB
Format:
Plain Text
Description: