A Hierarchical Wavelet-Based Framework for Pat tern Analysis and Synthesis

دانشگاه آزاد اسلامی اصفهان(خوراسگان)

منو

رکورد قبلی

رکورد بعدی

" A Hierarchical Wavelet-Based Framework for Pat tern Analysis and Synthesis "

Document Type	:	Latin Dissertation
Language of Document	:	English
Record Number	:	150899
Doc. No	:	ET22691
Main Entry	:	Clayton D. Scott
Title Proper	:	A Hierarchical Wavelet-Based Framework for Pat tern Analysis and Synthesis
Note	:	This document is digital این مدرک بصورت الکترونیکی می باشد
Abstract	:	Despite their success in other areas of statsitical signal processing, current wavelet-based image models are inadequate for modeling patterns in images, due to the pres-ence of unknown transformations inherent in most pattern observations. In this thesiswe introduce a hierarchical wavelet-based framework for modeling patterns in digitalimages. This framework takes advantage of the efficient image representations af-forded by wavelets, while accounting for unknown pattern transformations. Given atrained model, we can use this framework to synthesize pattern observations. If themodel parameters are unknown, we can infer them from labeled training data usingTEMPLAR? a novel template learning algorithm with linear complexity. TEMPLARemploys minimum description length (MDL) complexity regularization t o learn atemplate with a sparse representation in the wavelet domain. If we are given sev-eral trained models for different....-...,..tested for theQ1 PC1 bus cardBoth these projects mere sofixare des elopment efforts tonards contributing to dlfferentaspects of Roboucs and lZ1echatronics projects m the Controls and Roboucs Group..
Subject	:	Electericl tess
	:	برق
electronic file name	:	TL45917.pdf
Title and statement of responsibility and	:	A Hierarchical Wavelet-Based Framework for Pat tern Analysis and Synthesis [Thesis]