Please use this identifier to cite or link to this item:
http://hdl.handle.net/10603/428207
Title: | Object Extraction In A Quantum Inspired Soft Computing Environment |
Researcher: | Pal, Pankaj |
Guide(s): | Bhattacharyya, Siddhartha |
Keywords: | Computer Science Computer Science Artificial Intelligence Engineering and Technology Soft computing |
University: | Maulana Abul Kalam Azad University of Technology |
Completed Date: | 2021 |
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 |
Pagination: | xxiv, 162p. |
URI: | http://hdl.handle.net/10603/428207 |
Appears in Departments: | School of Engineering & Technology |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
01_title page.pdf | Attached File | 63.93 kB | Adobe PDF | View/Open |
02_priliminary pages.pdf | 57.83 MB | Adobe PDF | View/Open | |
03_content.pdf | 43.89 kB | Adobe PDF | View/Open | |
04_abstract.pdf | 34.53 kB | Adobe PDF | View/Open | |
05_chapter 1.pdf | 269.13 kB | Adobe PDF | View/Open | |
06_chapter 2.pdf | 174.99 kB | Adobe PDF | View/Open | |
07_chapter 3.pdf | 8.43 MB | Adobe PDF | View/Open | |
08_chapter 4.pdf | 10.76 MB | Adobe PDF | View/Open | |
09_chapter 5.pdf | 37.43 MB | Adobe PDF | View/Open | |
10_chapter 6.pdf | 40.78 kB | Adobe PDF | View/Open | |
11_annexture.pdf | 798.65 kB | Adobe PDF | View/Open | |
80_recommendation.pdf | 82.37 kB | Adobe PDF | View/Open |
Items in Shodhganga are licensed under Creative Commons Licence Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0).
Altmetric Badge: