Please use this identifier to cite or link to this item: http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/5983
Full metadata record
DC FieldValueLanguage
dc.creatorLumsdaine, A.-
dc.creatorWyatt, J.L., Jr.-
dc.creatorElfadel, I.M.-
dc.date2004-10-04T14:25:24Z-
dc.date2004-10-04T14:25:24Z-
dc.date1991-01-01-
dc.date.accessioned2013-10-09T02:42:11Z-
dc.date.available2013-10-09T02:42:11Z-
dc.date.issued2013-10-09-
dc.identifierAIM-1280-
dc.identifierhttp://hdl.handle.net/1721.1/5983-
dc.identifier.urihttp://koha.mediu.edu.my:8181/xmlui/handle/1721-
dc.descriptionImage smoothing and segmentation algorithms are frequently formulatedsas optimization problems. Linear and nonlinear (reciprocal) resistivesnetworks have solutions characterized by an extremum principle. Thus,sappropriately designed networks can automatically solve certainssmoothing and segmentation problems in robot vision. This papersconsiders switched linear resistive networks and nonlinear resistivesnetworks for such tasks. The latter network type is derived from thesformer via an intermediate stochastic formulation, and a new resultsrelating the solution sets of the two is given for the "zerostermperature'' limit. We then present simulation studies of severalscontinuation methods that can be gracefully implemented in analog VLSIsand that seem to give "good'' results for these non-convexsoptimization problems.-
dc.format51 p.-
dc.format7944553 bytes-
dc.format6223200 bytes-
dc.formatapplication/postscript-
dc.formatapplication/pdf-
dc.languageen_US-
dc.relationAIM-1280-
dc.subjectVLSI-
dc.subjectgraduated nonconvexity-
dc.subjectanalog networks-
dc.subjectresistivesfuses-
dc.subjectresistive grids-
dc.subjectsmoothing and segmentation-
dc.titleNonlinear Analog Networks for Image Smoothing and Segmentation-
Appears in Collections:MIT Items

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.